32 results about "Temporal similarity" patented technology

A method for computing similarity between paths includes extracting corpus statistics for triples from a corpus of text documents, each triple comprising a predicate and respective first and second arguments of the predicate. Documents in the corpus are clustered to form a set of clusters based on textual similarity and temporal similarity. An event-based path similarity is computed between first and second paths, the first path comprising a first predicate and first and second argument slots, the second path comprising a second predicate and first and second argument slots, the event-based path similarity being computed as a function of a corpus statistics-based similarity score which is a function of the corpus statistics for the extracted triples which are instances of the first and second paths, and a cluster-based similarity score which is a function of occurrences of the first and second predicates in the clusters.

The invention discloses a road network hot spot region mining method, belongs to the technical field of data mining and solves the problem when trajectory spatial-temporal similarity measurement and clustering calculation is adopted for trajectory clustering in the prior art. The method includes: step 1, performing trajectory segmentation on all trajectory sections, and calculating spatial-temporal similarity and spatial-temporal distance between two sub trajectory sections acquired after segmentation; step 2, performing clustering calculation on all trajectory section data in a grid space according to the spatial-temporal similarity and the spatial-temporal distance of the sub trajectories and a DBSCAN algorithm based on dynamic neighbor; step 3, selecting a remarkable class cluster set from class clusters of clustering calculation, and extracting stay spots from the remarkable class cluster set; step 4, according to the number of trajectory sections carried by the stay spots, acquiring hot regions of the stay spots, and acquiring hot spot regions in a road network from the regions where the stay spots are positioned. The method is used for spatial position locating.

A method for generating spatial-temporal consistency depth map sequences based on convolutional neural networks for 2D-3D conversion of television works includes steps of: 1) collecting a training set, wherein each training sample thereof includes a sequence of continuous RGB images, and a corresponding depth map sequence; 2) processing each image sequence in the training set with spatial-temporal consistency superpixel segmentation, and establishing a spatial similarity matrix and a temporal similarity matrix; 3) establishing the convolution neural network including a single superpixel depth regression network and a spatial-temporal consistency condition random field loss layer; 4) training the convolution neural network; and 5) recovering a depth maps of a RGB image sequence of unknown depth through forward propagation with the trained convolution neural network; which avoids that clue-based depth recovery method is greatly depended on scenario assumptions, and inter-frame discontinuity between depth maps generated by conventional neural networks.

The invention discloses a method for completing continuous missing data of dam deformation monitoring, which solves the problem of completing continuous missing data of dam deformation monitoring. Firstly, the continuity loss of deformation monitoring data is pretreated. Secondly, from the angles of global space, global time, local space, local time and semantics, the spatio-temporal similarity and functional similarity of deformation monitoring points are calculated respectively, and the missing data in deformation monitoring data are interpolated globally and locally in space, time and semantics. Finally, a depth neural network model is constructed to complete the continuous missing data in dam deformation monitoring. The preliminary results of the missing data are used as input, and thenonlinear fusion is realized by using the depth neural network representation ability.

The present invention discloses an HEVC fast coding method. During the coding process, the temporal similarity between optimal coding units of the same coordinate position in forward and backward reference frames, the spatial similarity between adjacent optimal coding units in the left and right direction, and the spatial similarity between adjacent optimal coding units in the up and down direction, are fully utilized to figure out the depth predicted values of P-frame or B-frame optimal coding units. After that, based on the one-to-one correspondence relationship between the depth predicted values of the optimal coding units and depth ergodic intervals, the depth ergodic intervals of the optimal coding units are determined. The optimal coding units and all coding units in the optimal coding units are coded within the depth ergodic intervals. During the coding process, qualified P-frame or B-frame optimal coding units and qualified coding units are selected quickly in the prediction mode, so that the unnecessary depth traversal and the unnecessary prediction-mode traversal are avoided. Therefore, on the premise that the video quality is ensured, the calculation complexity of the video coding is lowered.

The present invention discloses a vegetation loss direction identification method based on a multi-remote-sensing index trend. The method comprises: calculating a temporal similarity of vegetation indexes between each year and a beginning year by using a JM distance to generate a track of temporal similarity of vegetation indexes; extracting a potential vegetation loss region according to a variation of the temporal similarity of the vegetation index, so as to define a region where the vegetation index is significantly decreased and an impervious surface index is significantly increased as a vegetation loss region; and on this basis, finally determining different vegetation loss directions such as urbanization, desertification and wetland formation according to a water body index and a bare soil index trend feature. In the method, the vegetation change region is determined by using the variation of the temporal similarity, and further, the vegetation loss direction is determined according to multiple remote sensing indexes, without depending on manual intervention for threshold setting, so that the method has the characteristics of high robustness, high classification precision, high automation and storing anti-interference ability, and so on.

The invention discloses an intelligent substation intrusion scene restoration method and system based on spatio-temporal similarity matching. The method comprises the following steps: obtaining alarminformation of each alarm device of the intelligent substation; classification of alarm information; determining the alarm correlation relationship between alarm devices, and establishing the alarm similarity matrix between alarm devices; the causality matrix between alarm devices is established. Calculating the attack propagation probability between any two alarm devices, and determining the final attack propagation path between the alarm devices; according to the pre-established attack characteristics database of known attack types, the attack characteristics of known attack types are obtained. The alert information of each node in the attack scenario recovered from the final attack propagation path between the alert devices and the attack characteristics of the known attack types are analyzed for attack support respectively. The attack type with the most alarm devices in each node in the attack scenario is determined as the attack type of the current attack scenario.

The invention is applicable to the field of information technology, and provides a network topology reconstruction method and apparatus, and a terminal device. The method comprises the following steps: obtaining the number of network edges and the number of network nodes of a target network; simulating a propagation process of multiple pieces of information in the target network, obtaining an information recording matrix and an information arrival matrix, wherein the information recording matrix records data in which each network node is infected by one or more pieces of information, and the information arrival matrix records the time when each piece of information infects each network node; selecting any two network nodes infected by the same information, and calculating a time differencebetween the infection of the two network nodes according to the information recording matrix and the information arrival matrix; selecting two network nodes in which the time difference is a rate parameter to serve as similar node pairs; calculating the time similarity of the similar node pairs; and reconstructing the topological structure of the target network based on the time similarity and number of network edges. By adoption of the network topology reconstruction method and apparatus provided by the invention, the accuracy of predicting the missing links in the network topology can be improved.

The invention discloses a method and a system for calculating the urban land use mixing degree based on the social media data. Firstly, the time information, the position information and the text information of the social media data are obtained through a network crawler method. Then, an LDA topic model is introduced to extract dynamic text topics by constructing text documents with different timeintervals. Then, the temporal similarity and semantic similarity of dynamic text topics are calculated, and the calculating index of the urban land use mixing degree is constructed by using a hierarchical clustering model. Finally, based on the calculating index of the mixing degree, an information entropy algorithm is used to calculate the mixing degree of urban land use.

The invention discloses a low-illumination color video enhancement method by using a space-time illumination map. Firstly the initial space illumination map of the video frame is calculated, the timesimilarity illuminance map of the current video frame is calculated by using the initial space illuminance map of the current video frame and previous k video frames, the initial space illumination map and the time similarity illumination map are utilized to construct the structure weight matrix of the current video frame, the cost minimization model of the optimal illumination map estimation is constructed by using the initial space illumination map, the time similarity illumination map and the structure weight matrix and the solution is obtained as the optimal illumination map of the currentvideo frame, and finally the gamma correction is performed on the optimal illumination map and the enhanced current video frame is obtained by using the corrected illumination map. When all the videoframes are processed, all the enhanced video frames are combined to output the color video. The method can effectively enhance the illuminance of the low-illumination color video while maintaining the main structure in the video frame and makes the enhanced video have coherent illuminance.

The invention relates to the field of trajectory data processing, and discloses a spatio-temporal trajectory indexing and query processing method, device, equipment and medium. According to a received trajectory query instruction, it is determined that the trajectory query instruction belongs to ID time range query, spatio-temporal range query, spatio-temporal similarity query or KNN query; according to the method, comprehensive data processing is carried out on rich queries, multi-element query types are planned as a whole, complex upper-layer applications are supported, a uniform spatial-temporal trajectory index and query processing framework which can compress data, is light and efficiently supports the query types is designed, diversified query requirements are met, and the query efficiency is improved. The technical problem of optimal management of the spatio-temporal trajectory data is solved.

The invention belongs to the fields of criminal investigation and police research and judgment, police data mining, public security and criminal geography methods, and in particular relates to a method for identifying criminal gangs in consideration of the temporal and spatial semantics of trajectories. It mainly includes the following steps: (1) Clustering of trajectory points of key personnel; (2) Calculation of spatio-temporal similarity of trajectory of key personnel; (3) Calculation of spatio-temporal frequency of communication of key personnel; (4) Modeling of associated network of key personnel; (5) Criminal gang identification based on social network community discovery method. The beneficial effects of the present invention are that the judging index system of criminal gang relationship is perfected, it is not easy to cause misjudgment and missed judgment of criminal gang relationship, and members belonging to multiple criminal gangs can be judged at the same time, and can be used to identify non-criminal gang members, Improve the accuracy of identification of criminal gangs.

This disclosure is directed to techniques for determining a picture type for each of a plurality of frames included in a video sequence based on cross-correlations between the frames. The cross-correlations include first order cross-correlations between image information within pairs of frames included in the video sequence and second order cross-correlations between pairs of the first order cross-correlations. The first order cross-correlations may be analyzed to detect video transitional effects between the frames. The first and second order cross-correlations may be comparatively analyzed to determine temporal similarities between the frames. Therefore, the correlation-based determination techniques determine picture types for the frames based on the video transitional effects and the temporal similarities. The correlation-based determination techniques may calculate the first order cross-correlations between images within pairs of frames, or between sets of subimages within pairs of frames that are then averaged over the subimages for each of the pairs of frames.