127 results about "Space time correlation" patented technology

The invention relates to the technical field of movement behavioral analysis and prediction in a sense network environment, and specifically to a movement space-time trajectory analysis method in the sense network environment. The movement space-time trajectory analysis method in the sense network environment comprises data reception of receiving trajectory movement position data generated by a positioning device and resolving the data format into a data format applicable to data treatment; semantic treatment of performing clustering operation on the semantic trajectory data; space-time correlation of performing characteristic analysis and statistics on clustered semantic trajectory data in a time domain and a space domain, and performing time-space correlation analysis in combination with the time domain and the space domain; correlation similarity analysis of calculating space-time correlation similarity of the semantic trajectory and performing analysis and calculation on the correlation among different space domains and different movement objects; outputting a result. The movement space-time trajectory analysis method in the sense network environment solves the problem of continuous treatment and mutual correlation of time and space dimensions in a traditional transactional database, and meets the need from a sense network application service to real-time analysis of trajectory movement data.

The invention relates to the field of intelligent traffic, in particular to a dynamic traffic flow prediction method based on space-time correlation. The method comprises the steps that a space-time matrix is established after traffic flow data are preprocessed, an adjacent local linear reconstitution method is used for training the space-time matrix, a set of adjacent and weight values used for prediction are found out, prediction is conducted after non-negative correction, and at last the space-time matrix is updated through a prediction value. The dynamic traffic flow prediction method based on space-time correlation has the advantages that the adaptability is high, the method is suitable for any microwave detection road section; the feasibility is high, the data can be trained and predicted as long as a historical traffic flow database is given; the calculation speed is high, the complexity is low, and the calculation time is in a second level; the prediction precision is high, the randomness and volatility of dynamic data are removed, and the accuracy and reliability of a prediction result are improved; the prediction efficiency is high, multi-step traffic flow prediction of multiple five-minute time periods can be achieved, and high-efficiency short-time and long-time traffic flow prediction can be achieved.

The invention discloses an air pollutant concentration forecast method. The method comprises the following steps of determining a plurality of undetermined models and setting that a number of nodes of an output layer of each undetermined model is m; from historical concentration data, extracting a training data set and a verification data set; training each undetermined model till that the undetermined model is converged; determining the undetermined model corresponding to a minimum integration error to be a forecast model; and inputting a forecast data set into the forecast model, and taking an output result of the forecast model as a forecast result of forecast time delay r. By using the air pollutant concentration forecast method, based on a STDL model, forecast of air pollutant concentration is performed; implicit space-time correlation in air pollutant concentration data can be extracted; forecast data of a plurality of monitoring sites can be synchronously acquired and forecast precision is high; and precision of extreme air pollutant concentration forecast can be improved.

The invention provides an urban disaster thematic map real-time generating method based on network information. The method comprises the following steps that S1, the urban disaster information is obtained from networks in real time; S2, the urban disaster information is subjected to automatic place name recognition and is then subjected to spatial orientation; S3, the semantic mapping technology based on space time correlation rules is applied, and the urban disaster information subjected to the spatial orientation is subjected to semantic parsing; S4, the urban disaster information subjected to the semantic parsing is subjected to spatial data mining with graphic correlation, and the urban disaster thematic data with graphic spatial correlation is generated; S5, the urban disaster thematic data are subjected to visual representation, and an urban disaster thematic map is generated. The urban disaster thematic map real-time generating method has the advantages that the urban disaster information can be obtained in real time, the obtained urban disaster information is subjected to intelligent mining, the urban disaster thematic map is quickly generated and dynamically issued, and the quick generation and dynamical issuing level of the urban disaster thematic map is improved, and service is provided for urban management and emergency relief.

The invention belongs to the field of image processing, and discloses a space-time correlated channel massive MIMO transmission method. According to the space-time correlated channel massive MIMO transmission method, a time-shifted pilot frequency system structure is adopted, a user selection scheme based on the position of a user is utilized, user sub-groups having large interference in surrounding cells are omitted, so that data interference of the adjacent cells is reduced in a channel estimation stage, meanwhile, interference among the cells is reduced in a downlink data transmission stage, and system capacity is promoted. On the basis of the user selection scheme, a Kalman estimation method is adopted, a space-time correlation between channels is used, residual interference among the cells is eliminated further, and channel estimation accuracy is promoted. By means of combination of a user selection process and Kalman channel estimation, more accurate channel estimation results are obtained under the space-time correlated channel of a multi-cell massive MIMO system, interference among the cells in a pilot frequency estimation stage is restrained, and meanwhile the throughput rate of downlink data of the system is increased.

The invention provides a real-time traffic light recognition method based on space-time correlation and priori knowledge, and belongs to the field of traffic information detection in the intelligent transportation industry. The method includes the steps that firstly, regions of interest are positioned on an original image through the priori knowledge, and the regions unrelated to a traffic light are filtered out through empirical values; secondly, the red region and the green region of the traffic light are extracted and filtered on this basis through shape features; thirdly, sub-regions obtained through filtering are read in, the HOG features of the sub-regions are sequentially extracted, and a traffic light sample is trained through a classifier; fourthly, the current traffic light is recognized according to a discrimination function of the classifier, wherein if the front light is green, driving can be achieved, if the front light is red, a parking signal is sent out, and if both the green front light and the red front light exist, whether driving can be achieved or not is determined according to the space-time correlation information and lanes where vehicles are located. The method conforms to the detection and recognition characteristics of the traffic light, information of the traffic light can be accurately detected in real time, and the method is used in an intelligent vehicle and assists in correct and safe driving of the intelligent vehicle.

The invention discloses a traffic flow three parameter real time prediction method taking regard of space-time correlation. According to the method, on the basis of acquiring traffic flow rate, speed and occupancy data of a target section and upstream and downstream sections of the target section, a state space model for multivariable short time prediction of traffic flow three parameters is established; according to spatial correlation of various traffic variables at different data acquisition sections, an observation equation of the state space model is established; according to time autocorrelation and cross correlation of the multiple traffic variables at one same data acquisition section, a state equation of the state space model is established; prediction and iteration update of the traffic flow three parameters are realized by employing the Kalman filtering algorithm. The method makes full use of the spatial correlation of the traffic flow three parameters at the different data acquisition sections, the time autocorrelation and the cross correlation of the different traffic variables at one same data acquisition section, the multivariable prediction algorithm is employed, and thereby traffic flow short time prediction accuracy is facilitated.

The invention discloses a traffic sign identification system. The traffic sign identification system is characterized by comprising a high-dynamic camera which is installed at the position of an inner rear-view mirror of a vehicle, and the system collects traffic sign information of the road pavement ahead, then identifies traffic markings, traffic lights and traffic signs respectively from a road environment image and establishes corresponding space-time correlation models. Due to the structure and a method, time-space correlation criterions of traffic sign identification results are established by combination of time and space relationship, various traffic signs are identified in the same image, the traffic sign identification results are fused to acquire a credible output result, and influence caused by traffic sign identification error on intelligent driving is reduced.

The invention discloses a ground traffic sign real-time detection and recognition method based on space-time correlation, and belongs to the field of traffic information detection. An image Src of the road in front of an intelligent vehicle is obtained in real time through the frame rate of 20-50 frame/second, space correlation information is combined, cutting, grey level transformation, Gaussian filter, binarization processing and perspective transformation are performed on the obtained original image Src, and a perspective image Src_IP is obtained. A to-be-detected mark pattern diff_j is obtained through area filter and length-width ratio filter. Meanwhile, a processed ground traffic sign image temp_i is read in. Through image matching, the similarity between the diff_j and each standard image temp_i is calculated, and a set of most similar pictures is found. Subtraction is performed on the temp_i and the corresponding diff_j, statistics is performed on the number Sum_i_r of white pixel points in a new picture, and when the Sum_i_r is smaller than the set threshold value, it is considered that a ground traffic sign in the corresponding standard picture exists. The space-time correlation information is combined, logic judgment is performed on a recognition result, and the accuracy rate is improved. The method is suitable for intelligent driving in the complex city road environments.

The dynamic characteristic analysis method of real-time tendency of heart state includes: obtaining electorcardiac waveform with multipath electorcardiac amplifier and 12-bit A/D converter; forming time sequence related heart rate variation scatter diagram by means of space-time correlation technology and scatter diagram technology; extracting time sequence related characteristic parameters, short time-real time characteristic conversion illustration parameter and quantized space-time parameter indexes of characteristic illustration via automatic and manual interaction; classifying the illustration and quantized space-time parameters in artificial neural network; and describing dynamic characteristics and relevant invariance characteristics of heart rate variation in a nine-dimensional and a five-dimensional space with two independent curve surfaces and their boundary to represent the heart function.

The invention provides an urban road region congestion regulation and control strategy recommendation system and method. The space-time correlation between intersections is recognized to form a congestion group; priority ranking is carried out on the intersections in the congestion group, the intersection with the highest priority level is used as a key intersection, upstream and downstream intersections of space-time correlation type road sections of the key intersection are searched for, and an intersection regulation and control sequence recommendation is provided; a regulation and controltarget of the key intersection is decomposed into the intersections of the congestion group, and an intersection regulation and control target recommendation is provided; and according to features ofthe congestion group, corresponding regulation and control measure recommendations are provided. Rapid and real-time pushing of a regulation and control strategy is realized, and the efficiency of formulating the regulation and control strategy by timing personnel is improved.

The present invention relates to a method and device for repairing missing data in time-space sequence data, wherein the method includes: separately determining the contribution weights of space peripheral points and time peripheral points to the missing data points; The contribution weights of the points are sorted from large to small, and the spatial dimension estimation data of the points to be obtained are calculated; according to the contribution weights of the points to be obtained, the first multiple points are sorted from large to small Calculate the estimated data of the time dimension of the point to be sought for the surrounding points in time; calculate the data of the point to be sought based on the estimated data of the spatial dimension and the estimated data of the time dimension. The invention makes full use of the time-space correlation and heterogeneity of the time-space sequence data, and the obtained data of the point to be sought has high precision.

The present application relates to a traffic fusion analytical prediction method and system and an electronic device. The method includes the following steps of a: acquiring vehicle data information by using a fixed-point electronic photographing device in combination with a mobile intelligent information acquisition device, and acquiring mobile phone signaling data; b: separately extracting vehicle OD data and user OD data according to the vehicle data information and the mobile phone signaling data; c: constructing a network topological graph according to the vehicle OD data and the user OD data, and performing a space-time convolution operation on the network topological graph with space-time correlation by using a deep learning model based on a space-time diagram convolution network to establish traffic flow prediction model; and d: predicting a traffic flow and population distribution through the traffic flow prediction model. The method tracks and identifies the vehicle by means of the fixed-point electronic photographing device and the mobile intelligent information acquisition device, compensates for the limitation of video tracking fixed point identification and provides decision support for traffic control and induction in key areas.

The invention relates to a de-interlacing processing method which converts an interlacing video signal into a non-interlaced video signal; in the method, the interpolated field is processed with the motion detection based on the pixel point and the interpolation is processed correspondingly according to the result of the motion detection. During the motion detection process, the field with the time closest to the current acquisition time is selected; the field with the position the same to the position of the scanning line of the current field is selected; the space-time correlation is comprehensively considered to judge the motion state of the interpolated point. When an interpolation filter is designed, the edge exists in the image is acquired through the multi-directional edge detection and the analysis of the fake edge and the weak edge; the interpolation is correspondingly processed according to the motion state and the edge direction of the pixel point; the field resulted from the interpolation and the interpolated field are interlaced to form the non-interlaced video image. Compared with the prior art, the de-interlacing processing method can improve the subjective quality of the video and have the advantages of fast processing speed and strong anti-noise capability.

The invention relates to a method for compressing sensor network data based on optimal order estimation and distributed clustering. The existed data compressing method has low efficiency. The method utilizes the space-time correlation of the data acquired by the sensing node, and determines the initial data group numbers to be transmitted by the system by introducing the optimized stage estimation, thereby not only obtaining the effective correlation factor, but also avoiding producing redundancy factor; and on the other hand, executes clustering process on the network by using cluster as a unit processing node, so that not only the node data processing efficiency of the base station can be improved, but also the capacity that the base station can rapidly locate the position with abnormalvalues or abnormal nodes can be improved. The method provided by the invention is suitable for a real time environment control system based on the wireless sensor network, and can efficiently compress the data of the wireless sensor network, and efficiently reduce the average energy consumption of the node.

The embodiment of the invention provides a method and device for detecting equipment exception, and relates to the technical field of computers. The method comprises the following steps: obtaining a plurality of sample feature vectors of target equipment belonging to the same equipment type; for each negative sample feature vector, determining a positive sample feature vector which satisfies a preset space-time correlation degree condition with the negative sample feature vector, and forming a training sample set by the negative sample feature vector and the determined positive sample featurevector; training the initial neural network model through the training sample set to obtain an exception detection model corresponding to the target equipment; and when the to-be-detected feature vector of any target device is obtained, inputting the to-be-detected feature vector into the exception detection model to obtain an exception detection result of the target device, the to-be-detected feature vector being composed of a plurality of operation indexes of any target device collected at the same sampling time point. By adopting the method, the exception detection accuracy of the equipmentcan be improved.

The invention relates to a space-time correlation target re-identification method. The method, in combination with the pixel motion rate of a target in video data, probability distribution of the duration of the target crossing two fixed-distance adjacent cameras in each video data is estimated; based on the duration probability, candidate targets appearing in the video can be firstly screened andpreprocessed, candidate targets exceeding the reasonable crossing time interval are screened, and the probability that similar targets are mismatched to be tracking targets is reduced. The inventionfurther relates to a space-time correlation target re-identification system. The method is advantaged in that the generated matching result is constrained by the space-time position and the target motion information, compared with an original unconstrained matching structure only relying on visual features, re-identification accuracy can be effectively improved.

The invention provides a video steganography algorithm based on a motion vector difference MVD based on an H.264/AVC video coding and decoding framework. Through proving connection between the motion vector difference and motion vector space-time correlation, a statistics characteristic of the motion vector difference is used to design an embedding rule. Through combining a matrix coding algorithm, a series of matrix embedding secret keys with different sizes are designed and secret information is adaptively embedded into a video compression process so that the motion vector difference can well maintain an original histogram characteristic before and after steganography. The algorithm possesses good visual invisibility and can well resist steganography analysis based on motion vector space-time correlation.

The invention discloses a space-time correlation GLRT (generalized likehood ratio test) method based on oversampling. The method comprises the following specific steps: acquiring an oversampling signal sample matrix; calculating the average energy of receiving signals; calculating correlative statistic; calculating test statistic; and comparing the obtained test statistic with a preset judgment threshold to perform test judgment. According to the method disclosed by the invention, the average energy of the receiving signals is obtained through oversampling the receiving signals; and in the process of calculating the test statistic, the U calculation correlative statistic is obtained through utilizing the space-time correlation of an MIMO (multiple-input multiple-output) channel, namely utilizing the space-time correlation matrix eigen value decomposition of a normalization channel, so that compared with the existing frequency spectrum detection algorithm, the method disclosed by the invention has better detection performance, cannot be affected by noise variance estimation error and has strong robustness to the noise variance estimation error.

The invention discloses a short-long-term prediction method based on online taxi-hailing travel requirements. The method comprises the following steps of firstly, preprocessing data and segmenting thedata into a training set and a test set; then, dividing an urban road network into grids according to longitude and latitude and finding space-time correlation between areas; next, establishing a mixed model based on CNN+LSTM+XGBoost; and finally, predicting a taxi demand quantity within a short time period (such as 10 minutes) and a taxi demand quantity in a long time period (such as 1 hour, festivals and holidays and rush hours). The method can be used for short-term prediction such as prediction of traffic flow trends with intervals of 10 minutes, and can also be used for long-term prediction; and different periodic changes caused by weekends and festivals and holidays can be considered and different passenger flow rules in the rush hours every day are found out, so that the predictionaccuracy is improved.

The invention relates to a day-ahead optimization scheduling method considering a space-time correlation constraint of a wind farm, comprising the steps of: 1) building a robust unit commitment mathematical model which considers a power generation cost and a wind curtailment cost; 2) for a space clustering effect and a time smoothing effect of wind power, building a uncertainty set considering space and time constraint of the wind power; and 3) decomposing the mathematical model into a unit commitment main problem, a security feasibility inspection sub-problem and a wind power maximum utilization sub-problem, establishing a coupling relationship between the main problem and the sub-problems through a C&CG (Column and Constraint Generation) algorithm, and performing solving to obtain an optimization scheduling scheme. In comparison with the prior art, the day-ahead optimization scheduling method of the invention has the advantages of quick speed, reliability, high applicability, comprehensive consideration, good optimization effect, and so on.

The invention discloses an energy storage capacity optimal configuration method considering space-time correlation of forecast errors of various wind plants. The energy storage capacity optimal configuration method comprises the steps of analyzing a fitting effect on the forecast errors by comparing a parameter method with a non-parameter method, and selecting KDE method with highest fitting accuracy to perform error fitting; obtaining a joint distribution function of the forecast errors of various wind plants according to an actual space correlation of various wind plants by a modeling method of the space-time correlation of the forecast errors of various wind plants based on a Copula theory, and fitting an edge distribution function of the forecast errors by the KDE method; and building an energy storage capacity optimization model considering the space-time correlation of the forecast errors of various wind plants by taking minimum investment cost and running cost of an energy storage system as targets and by a multi-scene analysis method.

The invention discloses an efficient privacy protection perception big data collection method based on fog computing. A hierarchical fog computing auxiliary data collection framework is designed, so that a computing task can be processed on local equipment or network edge equipment, long-distance communication with a cloud center is avoided, and effective support is provided for exploring space-time correlation of perception data. Meanwhile, through the sampling disturbance encryption method, the data privacy is protected from being damaged by eavesdroppers and active attackers, the encryptionmethod does not damage the correlation of the data, and the decryption and reconstruction operation on the encrypted sampling data is simplified. Meanwhile, through the designed fog node data processing mode and anobservation matrix optimization model, the redundant data transmission amount is greatly reduced, the spatial correlation is effectively explored, and it is guaranteed that data can bereconstructed with high precision.

The invention discloses an end-to-end video super-resolution method based on adversarial learning and an attention mechanism in order to overcome defects that a traditional video resolution method ishigh in calculation overhead, low in calculation efficiency and incapable of efficiently processing a long sequence. According to the method, space-time correlation is extracted by adopting adjacent frame fusion and an attention mechanism, and a long sequence is processed at a time by adopting a circulating structure, so that a high-resolution reconstructed video rich in details and coherent in time sequence can be obtained. The video super-resolution method based on the attention mechanism and the adversarial learning has the advantages: 1, the novel video super-resolution method based on theattention mechanism and the adversarial learning is provided, and the super-resolution effect is improved; 2, the video super-resolution method based on the attention mechanism and the adversarial learning provided by the invention is better in effect; and 3, the video super-resolution can be applied to an actual scene, such as a monitoring device and a satellite image.