431 results about "No reference" patented technology

The invention discloses a no-reference structural sharpness image quality evaluation method, which comprises the following steps of: acquiring an original image input in a computer; preprocessing the original image, removing influence of isolated noise points on the sharpness of the original image and acquiring an original image to be evaluated; constructing a reference image for the original image to be evaluated through a low pass filter; respectively performing gradient calculation on the original image to be evaluated and the reference image, and extracting sub-image vectors with rich texture information; calculating the structural similarity between corresponding sub-image vectors so as to obtain structural similarity results of the sub-image vectors; and calculating no-reference structural sharpness by using the obtained structural similarity results of the sub-image vectors so as to obtain quality evaluation index no-reference structural sharpness of the original image. The reference image is constructed through an imaging model, no-reference image quality evaluation is performed by a reference image quality evaluation method aiming at image blurring, and the method is applied to the fields of imaging quality detection and control of an imaging system, evaluation of an image processing algorithm, and the like.

A method and system for image quality assessment is disclosed. The image quality assessment method is a no-reference method for objectively assessing the quality of medical images. This method is guided by the human vision model in order to accurately reflect human perception. A region of interest (ROI) of medical image is divided into non-overlapping blocks of equal size. Each of the blocks is categorized as a smooth block, a texture block, or an edge block. A perceptual sharpness measure, which is weighted by local contrast, is calculated for each of the edge blocks. A perceptual noise level measure, which is weighted by background luminance, is calculated for each of the smooth blocks. A sharpness quality index is determined based on the perceptual sharpness measures of all of the edge blocks, and a noise level quality index is determined based on the perceptual noise level measures of all of the smooth blocks. An overall image quality index can be determined by using task specific machine learning of samples of annotated images. The image quality assessment method can be used in applications, such as video/image compression and storage in healthcare and homeland security, and band-width limited wireless communication.

A method and a device for encoding/decoding video signals by motion compensated temporal filtering. Blocks of a video frame are encoded/decoded using temporal and spatial correlations according to a scalable Motion Compensated Temporal Filtering (MCTF) scheme. When a video signal is encoded using a scalable MCTF scheme, a reference block of an image block in a frame in a video frame sequence constituting the video signal is searched for in temporally adjacent frames. If a reference block is found, an image difference (pixel-to-pixel difference) of the image block from the reference block is obtained, and the obtained image difference is added to the reference block. If no reference block is found, pixel difference values of the image block are obtained based on at least one pixel adjacent to the image block in the same frame. Thus, the encoding procedure uses the spatial correlation between image blocks, improving the coding efficiency.

A no-reference estimation of video quality in streaming video is provided on a macroblock basis. Compressed video is being deployed in video in streaming and transmission applications. MB-level no-reference objective quality estimation is provided based on machine learning techniques. First the feature vectors are extracted from both the MPEG coded bitstream and the reconstructed video. Various feature extraction scenarios are proposed based on bitstream information, MB prediction error, prediction source and reconstruction intensity. The features are then modeled using both a reduced model polynomial network and a Bayes classifier. The classified features may be used as feature vector used by a client device assess the quality of received video without use of the original video as a reference.

A coherent laser beam combining system wherein the output of a single master oscillator is split into a plurality of N signals, and the N signals are electronically modulated at unique frequencies. There is no reference signal and all of the signals are passed through phase adjusters. All N signals are optically amplified, aligned and passed through a beam splitter to split off a small sample that is imaged onto a photodetector. The photodetector output is fed to a signal processor that separates the N signals and produces N phase error signals that drive the N phase adjusters resulting in a high-powered optically coherent output signal.

Methods and systems are provided for tracking object instances stored on a plurality of network nodes, which tracking enables a global determination of when an object has no references across the networked nodes and can be safely de-allocated. According to one aspect of the invention, each node has a local object store for tracking and optionally storing objects on the node, and the local object stores collectively share the locally stored instances of the objects across the network. One or more applications, e.g., a file system and/or a storage system, use the local object stores for storing all persistent data of the application as objects.

The invention discloses an objective evaluation method of no-reference video quality weighted by key frame image quality. The method comprises the steps of: firstly, preliminarily selecting a key frame according to a movement intensity method weighed by a human eye interest, then dividing the preliminarily selected key frame into a scene switching type key frame and a non-scene switching type key frame by correlation analysis; evaluating image quality of the non-scene switching type key frame, subdividing the non-scene switching type key frame into a content change type key frame and a quality change type key frame according to an evaluation result; finally carrying out weighted summation calculation on single frame quality by using a duration factor and a deterioration frequency factor of the quality change type key frame, and obtaining the quality evaluation result of an entire video sequence. According to the objective evaluation method, the defect that then existing evaluating technology cannot be coincided with an actual subjective feeling; computation complexity can be reduced on the premise of ensuring the evaluating performance; the objective evaluation method is suitable for automatic evaluation of various video applications of an existing network, simple in operating steps and easy to integrate.

The invention discloses a dynamic recommendation method based on training set optimization for a recommendation system, which specifically includes: (1) establishing a preliminary recommendation portion: generating an original recommendation model according to original user grading data; (2) performing AdaBoost trainings: utilizing the original recommendation model as a classifying and judging basis to classify the data and adjust learning times of samples by means of multiple iterative learning training data; (3) screening incorrect samples: data of selected difficult samples are removed as the incorrect samples after multiple AdaBoost trainings so as to construct a new training data collection; (4) reconstructing a recommendation model: combining training results to regenerate the recommendation model based on the new training data; and (5) generating recommendation results: utilizing the new recommendation model to generate the recommendation results. The method is capable of removing the data without referential meaning in recommended service by the aid of great relevance of original training set data in content, so that validity of the training data and precision of the final recommendation model are improved.

In a picture encoding apparatus which can reduce an amount of computation in encoding, frames are inputted in time series, and a scene change is detected. A scene number for identifying an identical or similar scene is assigned to each of the frames, and when a new scene appears, a new scene number is assigned. Picture frames having the same scene number assigned thereto, the frames being continuously inputted, are encoded in an inter-prediction mode. With respect to a frame inputted after a scene change, a search is made for a reference picture in accordance with a scene number. If no reference picture exists, encoding is carried out in an intra-prediction mode. If a reference picture exists, the frame is encoded in any one of the intra-prediction mode and the inter-prediction mode so as to minimize an encoding cost.

The invention relates to a voice state detection method suitable for an echo cancellation system. The voice state detection method relates to the field of voice interaction technologies based on an IP network. The voice state detection method comprises the steps of: constructing a support vector machine (SVM) classifier by utilizing noise training samples and voice training samples, wherein signals to be detected are far-end and near-end signals after blocking, carrying out VAD judgment on the block far-end signal by adopting the constructed SVM classifier based on a Gaussian mixture model, stopping updating and filtering of a filter and outputting a near-end voice signal directly if the judgment result is that no voice exists, and carrying out double-end conversation judgment when judging that voice exists at a far end; stopping updating coefficients of the filter when in double-end conversation, and filtering the near-end signal; otherwise, conducting coefficient updating and filtering of the filter according to the far-end signal. The voice state detection method improves accuracy of voice activity detection, prevents a double-end mute state from being misjudged to be a double-end conversation state, and prevents error updating and filtering of the filter without a reference signal.

The invention discloses a quality objective evaluation method with no reference images based on multi-scale generative adversarial network. Similar quality images corresponding to distorted images canbe generated through the multi-scale generative adversarial network, and similar quality images in different scales can undergo regression to obtain the image quality scores through convolution nervenetwork. The multi-scale generative adversarial network is trained, and similar quality images are generated for the distorted images through the full-reference image quality evaluation method, and the similar quality images are considered as a real data set for determining network. Three groups of similar quality images in different scales are considered as the data set, and the subjective evaluation score is used as the label, and the image quality score regression network is trained. The distorted image generates a plurality of similar quality images in different scales through the generative network, and generates the image quality score through the image quality score regression network. The invention is advantageous in that the integral distortion degree and the local distortion details are combined, and the quality score of the distorted images can be further determined, and the quality of distorted images can be embodied in a more comprehensive and more accurate manner.

The invention discloses a realization method and an inspection system for intelligent inspection and route planning based on cloud computing. The method comprises the following steps: the inspection track of an inspection mobile terminal is reported; the track data reported by the inspection mobile terminal is preprocessed, and drifting data points are filtered; road network data is generated according to a large amount of track data; all kinds of facilities needing inspection, key inspection points and other data are marked; a route planning line is generated according to the road network data and the marked points of inspected facilities and automatically updated; and electronic map and planning line fused navigation is provided on the inspection terminal. The nearby road network and the planning line can be checked conveniently during an inspection task, and the work of the inspection personnel is facilitated greatly. A road network and a planned route of inspection can be generated according to the historical inspection track. The problem that an inspection area is void and has no reference route on common maps is solved.

The invention supplies a intercross type complex array sensor of ECT/ERT double mode imaging system, the sensor installed in the tested object Pipeline, it includes the same electrode number ECT electrode array and ERT electrode array which equalize, across installed in the inner/outer wall of tested object Pipeline, the electrode number is 8 to 64 in the ECT and ERT electrode array, it installed ERT electrode between every two ECT electrode; it installed shielded enclosure out of the related ERT electrode. Its beneficial effects is that it can obtain the information flow at the same time, the same location of the measured fluid when it use the sensor, at the same time, it can obtain measuring information at more direction which is benefit for raising the quality of restored two modal system imaging. When ECT electrode array works, no reference to the cut state of simulate electron switch, ERT electrode as shielded electrode would not interfere ECT electrode array working, on the contrary ERT electrode could reduce the dynamic range of the measured capacitance, and benefit for measuring ECT system, the reverse is true.

The invention provides a no-reference video quality evaluating method, and aims to solve the problems of low relevance between an objective MOS value and a subjective MOS value output by the conventional method, weak prediction accuracy and weak generalization ability thereof. The method comprises the following steps: extracting blocking effect parameters, blur parameters and code rate parameters of video received by a receiving end; setting motion complexity parameters for the video according to the decoded time domain of the video; outputting the objective MOS value by using an evaluation model which is acquired in advance based on support vector (SV) regression (SVR) according to the blocking effect parameters, the blur parameters, the code rate parameters and the motion complexity parameters; and acquiring higher relevance with the subjective MOS value. On characteristic parameter selection, TS stream parameters are integrated with main sense injury parameters; and the evaluation model determining method adopts a method of the support vector regression. The method is applicable to videos in different resolution ratios, in particular to videos with encoder injury.

The invention relates to a no-reference image quality evaluation method based on a convolutional neural network. The method comprises the following steps that: S1: carrying out local normalization processing on training images in a training image set; S2: dividing the training images into blocks of different scales in an overlapping way; S3:utilizing the convolutional neural network to learn the characteristics of blocks of different scales, and inputting a plurality of characteristics generated on different scales into three fully connected layers to learn the quality evaluation score of theblock; and S4: utilizing the trained convolutional neural network to predict the quality evaluation scores of all blocks of an image to be predicted, and calculating the average quality evaluation score of all blocks of the image to be predicted as the final quality evaluation score of the image. By use of the algorithm, the characteristics of the image on different scales are comprehensively considered, and no-reference image quality evaluation performance based on the convolutional neural network can be obviously improved.

A method for mapping wireless resources of reference symbols for channel state estimation and modulation symbols for user information transmission in a transmitter of an Orthogonal Frequency Division Multiplexing (OFDM) mobile communication system is disclosed. The mapping method includes channel-encoding and modulating a user information stream to be transmitted, and then generating a systematic symbol stream and a parity symbol stream; and preferentially arranging systematic modulation symbols in resource elements of a symbol including no reference symbol, and then arranging parity modulation symbols in remaining resource elements.

The invention discloses a no-reference image quality evaluation method based on a fully convolutional neural network. A full reference image quality evaluation method is adopted to obtain the objective and real quality map of each distorted image in a training set as supervision to train the normalized image of all distorted images in the training set, and an optimal fully convolutional neural network regression training model is obtained; the normalized image of the distorted image to be evaluated is input into the optimal fully convolutional neural network regression training model; the objective quality evaluation prediction quality map of the distorted image to be evaluated is predicted; and the saliency map of the distorted image to be evaluated is used for carrying out weighted pooling on the objective quality evaluation prediction quality map so as to obtain an objective quality evaluation prediction value. Since various features, including full reference features, saliency features and the like, of the distorted image are combined and the features can accurately describe the distorted image, dependency between the objective evaluation result and subjective perception is effectively improved.

An imaging-type interferometric optical profiler splits a beam reflected from a sample into two beam portions. One portion is a reference beam and the other a sample beam. The reference and sample beams are combined to create interference patterns which are used to obtain a surface profile of the sample. Since vibration of the sample causes the same optical path change, and no reference mirror is used, the interferometric optical profiler is relatively vibration-insensitive and has a fast measurement speed.

The invention provides a system and method for selecting an optimal multimarker reagent combination for the identification and/or quantification of molecules in or on cells with or without reference to fluorescence or other properties of at least one fluorescent dye or other instrument-measurable atom or molecule associated directly or indirectly with the reagent combination. The method includes specifying, using a computer, a plurality of markers to be detected by a plurality of reagents, generating, using a computer, a plurality of reagent combinations comprising the plurality of reagents to detect the plurality of markers, wherein the reagent combinations are ranked according to at least one user-defined or system-defined criterion, and selecting the optimal reagent combination or providing a rank-ordered list of combinations.

The invention relates to a PM2.5 (Particulate Matter2.5) concentration detector based on definition evaluation without a reference image. The PM2.5 concentration detector mainly comprises an image definition evaluation unit, a laser ranging unit and a PM2.5 concentration display unit, wherein the image definition evaluation unit works as follows: images of target objects in different distances are shot by a camera, the images are converted into grayscale images, the grayscale images are segmented into 64*64 pixel blocks by adopting a no-reference-image definition evaluation method, the 64*64 pixel blocks are compared with the preset threshold value T equal to 0.2%, the edge blur detection probability P(BLUR) of the segmented edge pixel blocks is calculated, then the fuzzy cumulative probability CPBD value of the whole grayscale images is calculated, the fuzzy cumulative probability CPBD value is compared with the interval (minimum P-maximum P) of the CPBD threshold value P of the optimal visibility image and the CPBD value of the better image, and the target object to be detected is determined; the laser ranging unit is used for measuring the distance of the target object to be detected and determining the visibility distance value; the PM2.5 concentration display unit is used for calculating and displaying the PM2.5 concentration according to the relations of the scattering coefficient and the visibility as well as the scattering coefficient and the PM2.5 concentration.

The invention relates to a no-reference image definition detection method. The method comprises the following steps of: firstly, calculating a gradient map according to the existing grey-scale map; secondly, positioning strong edge points by using an open edge detection algorithm; thirdly, calculating the edge width of each strong edge point to obtain an edge width cumulative histogram; fourthly, carrying out wavelet transform on the existing gray-scale map, and calculating the energy of high-frequency wavelet coefficient; fifthly, counting a grey-scale histogram according to the existing grey-scale map, and calculating the feature of the grey-scale histogram according to the grey-scale histogram; and finally, estimating the definition of the grey-scale map according to the edge width cumulative histogram, the energy of high-frequency wavelet coefficient and the feature of the grey-scale histogram. According to the method, the definition of images can be detected without reference images, and the definition value is consistent with the subjective feeling of eyes. The method is not influenced by the image content and the luminance of the field of view, and the detection result has a certain robustness to interferences such as coding and noise.

The present invention relates to a quality blind evaluation method for an unmanned aerial vehicle image. The method comprises the steps: S1, obtaining an unmanned aerial vehicle image, and performing analysis at three aspects of the image information structure character, the image information integrity and the image information color character; constructing the corresponding quality evaluation measurement; and constructing a standard MVG model by employing a multi-Gaussian beam model, and finally obtaining the quality equal division of the whole image by employing a mean value method. On the basis of comprehensively analyzing the classic no-reference image quality evaluation method and unmanned aerial vehicle image features, aiming at the unmanned aerial vehicle image multi-distortion and mixture problem, the quality blind evaluation method for an unmanned aerial vehicle image extracts three types of quality feature factor sets capable of showing the unmanned aerial vehicle image multi-distortion scenes for perception expression for three types of main distortion of information entropy integrity, structure information changing and color loss.

The invention relates to a method for synchronization of clock sources in a communications system, in particular a radio communications system, having a large number of devices (PSTN, MSC, RNM, BSi, MSi, OMC) which communicate directly or indirectly with one another and have reference clock sources (Cs) for their operation.

In order to overcome aging effects or timing errors in the clock sources (C), the invention proposes the clock sources (C) of one or more communicating devices (MS, BS, RNM) be synchronized by means of asynchronous signaling from at least one reference clock source (Cs). This even allows devices with clock sources that are becoming old to be operated reliably. Furthermore, in particular, there is no need for every device to have its own high-precision clock source (CS). Use is particularly advantageous in communications systems in which no reference clock is transmitted via a landline network.

The invention relates to a no-reference image quality evaluation method based on Curvelet transformation and phase coincidence. The no-reference image quality evaluation method based on Curvelet transformation and phase coincidence comprises the following steps: (1), images are transformed to a Curvelet domain and a phase coincidence domain; (2), a series of natural scene statistical characteristics are extracted from the Curvelet domain and the phase coincidence domain; the series of natural scene statistical characteristics comprise logarithm histogram peak value coordinates of Curvelet coefficients and phase coincidence coefficients, direction energy distribution characteristics and dimension energy distribution characteristics; and (3), a two-step frame is used, the series of characteristics extracted in the step 2 and a support vector machine are utilized for firstly classifying distorted images of unknown types, and then nonlinear regression of a specific type is conducted on the distorted images according to a classification result, and DMOS is forecasted according to an objective quality evaluation result of the images. The no-reference image quality evaluation method based on Curvelet transformation and phase coincidence has the advantages of being high in human eye subjective consistency, small in time complexity, and high in application value.

The embodiment of the invention discloses a video thumbnail generation method and device. The method comprises the following steps: carrying out scene boundary detection on a video, and sectioning the video according to different scenes; from all sections of the video, selecting a section with the longest duration as a key section; from all video frames contained in the key section, selecting a video frame with the highest balance as a key video frame; and compressing an image of the key video frame so as to generate a thumbnail to be used as the thumbnail of the video. The video thumbnail generation method and device disclosed by the embodiment of the invention can solve the problems that in the prior art, by analyzing each video frame of the whole video to generate the thumbnail, the calculation amount is large, and the efficiency is low; the invention also solves the problem that in the prior art, a video frame having no reference value for the video content is used as the thumbnail of the video; and a video frame which represents the video content and has a reference value for users can be captured as the thumbnail of the video.