124 results about "Spatial consistency" patented technology

A director is provided to receive source address instances of packets routed through routing devices of a network. The director determines whether any of the reported source address instances are to be deemed as spoof source address instances. The director further determines where filtering actions are to be deployed to filter out packets having certain source addresses deemed to be spoof instances. The director makes its determinations based at least in part on a selected one of a number of consistency measures. The consistency measures may include but are not limited to spatial consistency, destination consistency, migration consistency, and temporary consistency. The consistency measures are evaluated using spatial, destination source address range, migration and timing S/D/M/T distribution profiles of the reported source addresses. In some embodiments, the determinations are based further in view of reference S/D/M/T distribution profiles, which may be an exemplary S/D/M/T distribution profile of a typical non-spoof source address or a historical S/D/M/T distribution profile of the source address.

A method that facilitates identification of features in a scene enables enhanced detail to be displayed. One embodiment incorporates a multi-grid Gibbs-based algorithm to partition sets of endmembers of an image into smaller sets upon which spatial consistency is imposed. At each site within an imaged scene, not necessarily a site entirely within one of the small sets, the parameters of a linear mixture model are estimated based on the small set of endmembers in the partition associated with that site. An, enhanced spectral mixing process (SMP) is then computed. One embodiment employs a simulated annealing method of partitioning hyperspectral imagery, initialized by a supervised classification method to provide spatially smooth class labeling for terrain mapping applications. One estimate of the model is a Gibbs distribution defined over a symmetric spatial neighborhood system that is based on an energy function characterizing spectral disparities in both Euclidean distance and spectral angle.

The invention discloses a deep learning saliency detection method based on the global a priori and local context. The method includes the steps of firstly, performing superpixel segmentation for a color image and a depth image, obtaining a global a priori feature map of each superpixel based on middle-level features such as compactness, uniqueness and background of each superpixel, and further obtaining a global a priori saliency map through a deep learning model; then, combining the global a priori saliency map and the local context information in the color image and the depth image, and obtaining an initial saliency map through the deep learning model; and finally, optimizing the initial saliency map based on spatial consistency and appearance similarity to obtain a final saliency map. The method of the invention can be used for solving the problem that a traditional saliency detection method cannot effectively detect a salient object in a complex background image and also for solving the problem that a conventional saliency detection method based on deep learning leads to false detection due to the presence of noise in the extracted high-level features.

The invention discloses an image retrieval method, an image retrieval device and an image retrieval system, wherein the image retrieval method comprises the following steps: extracting the local features of a query image, and quantizing the local features into visual words; querying a preset visual-word inverted list in an image database by using the visual words so as to obtain matched local-feature pairs and matched images; respectively carrying out space encoding on relative space positions between matched local features in the query image and the matched images so as to obtain a space code picture of the query image and space code pictures of the matched images; executing a space consistency check on the space code picture of the query image and the space code pictures of the matched images so as to obtain the number of the matched local-feature pair in conformity with the space consistency; and according to the numbers of the matched local-feature pairs (in conformity with the space consistency) of different matched images, returning to the matched images according to the similarity of the matched images. By using the method provided by the invention, the image retrieval accuracy and the retrieval efficiency can be improved, and the time consuming for retrieval can be reduced.

The invention is a system for and a method of maintaining namespace consistency in a wide-area file system. In one embodiment, a wide-area file system has a plurality of replicas for a file. Each replica of a file and parent directories for the file are at a node. An update to a replica of the file is propagated to other replicas of the file. In response to receiving a propagated update to a replica at a node, the replica for the file at the node is updated. A directory operation (e.g., rename, link or unlink) may affect a backpointer for a replica. When a backpointer for a replica at a node is not consistent with the parent directories for the replica at the node, the the parent directories are modified to be consistent with the backpointer. A modification may be performed at a node while an earlier inconsistent modification may be ignored. As a result, consistency is maintained among the replicas.

The invention relates to video copy detection system and method, which are used for fast and accurately checking that whether input copies a video segment in a video data set and outputting a beginning position and an end position in the presence of copied segment according to a query video input by users. The method comprises three steps of feature extracting, feature matching and amalgamation judging. The SURF (Speeded Up Robust Features) feature of a video frame is firstly extracted, an optimization scheme of an integrogram is utilized in the extraction process of the feature, and the extraction speed is high. The feature matching step is different from traditional methods for matching feature vectors of each feature point, and adopts a two-layer matching method which comprises the following steps of: firstly, adopting a bag-of-words method on the feature vectors of each key frame, obtaining a word frequency histogram of the key frame, and then indexing the word frequency histogram of each key frame for researching a matched key frame pair; and finally matching the feature points in the key frame pair. In the amalgamation judging step, a probabilistic graphical model is established for PSE (Product Safety of Electrical Appliance and Materials), a powerful reasoning method is utilized for deducing the existence and the position of the copied segment, fully the time consistency and the space consistency of the video are fully utilized, and the disadvantages of traditional amalgamation methods are avoided.

The invention discloses a low-altitude remote sensing image high-precision matching method with consistent image space. Firstly, SURF feature matching is carried out on the top layer of an image pyramid, and an affine transformation relation between a base image and a search image is built; then, feature point extraction is carried out on the base image, the affine transformation relation is used as a geometric constraint condition, a feature point window is switched to the search image, meanwhile, a window of the search image is corrected and re-sampled to be in an image space coordinate system of the base image, correlation coefficient matching is carried out, polynomial iteration is used for removing a gross error, obtained corresponding image points are utilized for resolving and updating the affine transformation relation between the base image and the search image again, and then the lower-layer image matching is carried out until bottom-layer image matching; finally, a matching result is converted to be under an image space coordinate system of the search image, and high-precision least squares matching is carried out. The method solves the problems that due to the fact that the problems of large rotating, geometry deformation and the like exist in the image space, the matching success rate is low, and a failure easily happens, and the matching efficiency and the success rate of a low-altitude image are greatly improved.

The invention belongs to the technical field of remote sensing image processing, and particularly relates to a hyper-spectral remote sensing image semi-supervised classification method based on ground object class membership grading. On the premise of over-segmentation, membership grading serves as a kernel, region growing procedures are introduced, spectral information and space information are effectively combined, and a new strategy is provided for semi-supervised classification, wherein the fuzzy theory serves as the basis of membership grading, and three factors, namely spatial consistency of hyper-spectral images, spectrum variability and prior knowledge, are synchronously weighed so that a high-precision classification result and a smooth classification identification graph can be obtained. The method has good robustness in terms of the occupied ratio of parameters and training samples in total samples. The prior knowledge is efficiently used in fuzzy grading of ground object class membership, only a few training samples are needed to output the high-quality classification result, and classification precision is not sensitive to changes of the parameters. The method has important application value in classification of the hyper-spectral images.

The invention discloses a full-tensor magnetic field gradiometer based on the giant magnetic impedance effect. The full-tensor magnetic field gradiometer comprises an X-Y-direction gradiometer body, a Z-direction gradiometer body and signal leads. The X-Y-direction gradiometer body comprises a cross-shaped substrate and a giant magnetic impedance thin film, the Z-direction gradiometer body comprises a rectangular substrate and a giant magnetic impedance thin film, a junction point at the input end and a junction point at the output end of an electric bridge are connected with the signal leads, and the signal leads are arrayed symmetric with the geometric center of the whole gradiometer as the three-dimensional center. The full-tensor magnetic field gradiometer has the advantages of being high in accuracy, minimized, low in cost, wide in frequency response, rich in information and the like. Due to the design of preparing a three-dimensional structure through planar thin films, the problem of space consistency of the full-tensor magnetic field gradiometer based on the giant magnetic impedance thin films is solved, and the magnetic field gradient measuring sensor with the size at the chip level is designed for the first time.

The invention discloses a hyperspectral remote sensing surface feature classification method based on superpixel-tensor sparse coding, and irons out the defects that the prior art cannot makes the most of the spatial information of a hyperspectral image to carry out classification and is low in classification speed. The method comprises the steps: (1) inputting a to-be-classified hyperspectral image; (2) building a hierarchical spatial similarity matrix; (3) obtaining a superpixel set; (4) building a mark sample dictionary; (5) solving a sparse coefficient matrix; (6) classifying superpixels; (7) outputting the classification results of the to-be-classified hyperspectral image. The method is advantageous in maintaining the spatial consistency of homogeneous regions of the hyperspectral image and being high in classification speed, and can be used for the rapid classification of the hyperspectral image.

The invention discloses a high-precision dip estimation method, which comprises the following steps of: firstly, calculating a gradient vector; then, turning over a vector field; calculating the vector set distance; calculating vector filtering weighting; and finally, carrying out vector weighting filtering processing. According to the method, the space consistency of dip estimation in a lineup single-direction extending area can be kept, and the dip estimation precision of the dip estimation method on a fault and the stratum structure with angular unconformity and fold morphology is improved. The algorithm content of the technical scheme is easy to realize and has high calculation efficiency. Meanwhile, the size of an analysis window can be flexibly regulated to satisfy the requirement of different dip estimation effects; for seismic data with severe noise interference, the space consistency of the dip estimation result can be improved by adopting a big analysis window; and for seismic data with a high signal to noise ratio, the dip estimation result precision of the fault and the angular unconformity area can be improved by adopting a small analysis window.

The invention provides a construction method and device of a three-dimensional map, a robot and a readable storage medium. The construction method and device are used for improving the spatial consistency of the three-dimensional map in the aspect of semantic information. The method comprises the steps that a construction device receives a construction request initiated by UE, and the constructionrequest is used for requesting to construct a three-dimensional map of a target scene; the construction device obtains map collection information of the target scene, wherein the map collection information comprises an RGB image, three-dimensional point cloud information and a depth image of the target scene; the construction device carries out super-pixel grouping on the RGB image through an SLIC algorithm to obtain a super-pixel image; the construction device converts the three-dimensional point cloud information into a three-dimensional grid image; the construction device performs semanticsegmentation on the RGB image and the depth image through a coding and decoding type semantic segmentation model to obtain a semantic image; and the construction device fuses the three-dimensional grid image, the super-pixel image and the semantic image to obtain a three-dimensional map of the target scene.

The invention provides an abnormal behavior detection method based on a large-scale WiFi activity track. The method comprises the following steps: on the basis of a collected MAC record, finding MACs with normal individual behaviors by using a frequent track mining algorithm, extracting the activity feature attributes of these MACs with normal individual behaviors to serve as the input of an SVDD algorithm, establishing a plurality of abnormal behavior detection models to filter a large number of MACs satisfying group behavior rules, thereby not only greatly shortening the time necessary for processing large-scale data, but also ensuring the stability of the abnormal behavior detection method, the feature of serious unbalance of positive and negative samples in the application environment can be well overcome, and accordingly time consistency and space consistency detection is carried out on a single MAC different from the group behavior rules to lock the MAC with abnormal activity more accurately. By adoption of the abnormal behavior detection method provided by the invention, the moving track of a moving object in the public security field can be monitored in real time, abnormal behaviors can be identified accurately in real time, auxiliary judgment is provided for the happening security events, and early warning is provided for the possible security events.

The invention provides an integrated smart data acquisition method and platform based on surface meteorological observation. The method comprises: S1, collecting current meteorological data of a dual-set automatic weather station including an A station and a B station and uploading the data to a first remote server and a local server; S2, analyzing the current meteorological data, carrying out data quality control (including data missing detection, data consistency, time consistency, spatial consistency) to obtain message data, and monitoring the data quality control process; and S3, carryingout uplink of the message data to a second remote server and monitoring an uplink state of the message data. Therefore, automatic verification of the dual-set automatic weather station is realized andthe accurate meteorological data files are obtained; real-time reporting is carried out while abnormity occurs in data collection, data transmission, and data observation; unmanned attendance of theweather monitoring station and automatic and intelligent meteorological observation services are realized; the administration staff is able to manage the observation services objectively, quickly, andcomprehensively.

The embodiment of the invention provides an image retrieval method and an image retrieval device. The method comprises the following steps: matching feature points of a queried image with visual words of a visual word list to obtain a first visual word collection; matching feature points of a candidate image with visual words of the visual word list to obtain a second visual word collection; determining a third visual word collection; aiming at the visual words in the third visual word collection, determining a feature point collection of the candidate image and a feature point collection of the queried image matched with the visual words in the third visual word collection; determining the space consistency similarities of the feature point collection of the candidate image and the feature point collection of the queried image; adding the space consistency similarities to obtain the space consistency similarities of the candidate image and the queried image; according to the space consistency similarities, determining the targeted retrieval image of the queried image. The image retrieval method and the image retrieval device, disclosed by the embodiment of the invention, can improve the accuracy of image retrieval.

The invention provides a road extraction method based on fully convolutional network ensemble learning to obtain a road extraction result with coherent roads, complete road network structure and a high recall ratio. The method comprises steps of: firstly, selecting a sample set from an existing remote sensing database and dividing the sample set into a test sample and a training sample; secondly,training a fully convolutional neural network with cross entropy as a loss function, then changing the positive sample penalty weight of the loss function, optimizing the positive sample penalty weight on the basis of the network model parameters of a previous network to obtain the fully convolutional neural network of the loss function with different penalty weights; extracting the roads by usingthe trained fully convolutional neural network to obtain road extraction results of different fully convolutional networks; and finally, according to the principle of spatial consistency, integratingthe different extraction results according to the spatial consistency-based integration strategy, and outputting the final result map. The method can improve the recall ratio of the road extraction result and has good robustness.

A computer-implemented method is described. The method is performed upon a multi-orientation display device and includes displaying a plurality of graphical elements within a User Interface (UI) upon the display device, where the plurality of graphical elements have a respective first aspect ratio, reorienting the UI with respect to the display device, and adjusting the plurality of graphical elements to have a respective second aspect ratio in response to the reorienting.

Distinct Groupings of Related Objects for Display in a User Interface Display of related objects in a user interface. An index value (or other identifier) is associated with each resource in a particular resource group, and this index value enables grouping the resources when a representation of the group is displayed. Spatial consistency may be maintained by displaying the resource groupings in order by their index value, and this order may be maintained over time as the displaying is repeated. The resources in the groupings may correspond to nodes and links in message flows. Preferably, the resources are dynamically determined by observation of their interactions, such as observing the participation of nodes and links in message flows.

The invention discloses a feature matching method based on depth re-projection and space consistency, and the method comprises the following steps: obtaining an RGBD image and a depth image through anRGBD camera, generating a three-dimensional point cloud, and extracting a plane through RANSAC; performing feature point extraction on the generated point cloud image by using ORB, and establishing adescriptor; establishing a rough corresponding relation between the two frames through a KNN algorithm; obtaining a more reliable corresponding relation by utilizing the space consistency of featurepoints, carrying out feature matching, giving 3D coordinates, and obtaining reliable matching features through graph optimization. According to the method, the corresponding relationship between the frames is extracted more reliably by utilizing the spatial consistency of the feature points, so that the accuracy and robustness of feature matching are improved.

The invention belongs to the field of remote image processing technology, in particular to a merging method of membership scoring based on ground object categories under a spatial-spectral combined classification frame for hyper-spectral remote sensing images. In the method, a ground object classification mark graph with high precision is obtained finally in combination with a primary classification result based on spectral information and a primary partition result based on spatial information, and a new strategy is provided to the merging section of a classification, partition and merging frame. Three factors, including spatial consistency of hyper-spectral remote sensing images, spectral variability and transcendental knowledge are balanced synchronously by using the fuzzy theory as the basis and the membership scoring as the core, so that the classification precision can be improved effectively, and the spatial smoothness and the readability of the classification mark graph can be strengthened. Meanwhile, the merging method has good compatibility and robustness and can cope with many uncertainty factors such as low-precision primary classification, partition results and parameter variation; and the practicability of the spatial-spectral combined classification frame can be improved. The merging method has important application value in the classification of the hyper-spectral images.

The invention relates to a sample double sparse image inpainting method based on the features of Facet directional derivative, which includes the following steps: S1, acquiring directional feature information of an image in different directions under a Facet model; S2, using an improved inpainting priority calculation function to sort image blocks to be inpainted; and S3, inpainting the damaged region with the highest inpainting priority determined in S2 through sparse representation of candidate image blocks. Directional features are fully utilized in the method. A new image block distance calculation function is constructed, and the space consistency and continuity constraints of the directional features are added in the sparse solving link. Meanwhile, the inpainting priority calculation function is adjusted and improved, and the confidence values of the image blocks are controlled within a reasonable range, in order to ensure the reliability of the priority calculation result. Both the color information and directional feature information of the image are considered, and all kinds of image damage situations can be dealt with. The method has good universality and wide market prospect and application value.

The invention discloses a road width estimation method based on a high-resolution satellite image. A novel road width descriptor is defined according to the characteristics of a road in a high-resolution satellite image. The width features of a road can be described by doing statistics of pixel distribution in road blocks of fixed size and representing pixel distribution with a histogram. On the basis of the road width descriptor and a convolutional neural network, a road width estimation method based on a convolutional neural network is presented. In view of width discontinuity in the road width estimation result, a road width estimation energy function based on space consistency is defined according to the continuity of road width. The category of road width in a satellite image can be estimated reasonably by minimizing the energy function.

The invention provides a copper coil-based full-tensor magnetic field gradient measurement device. The copper coil-based full-tensor magnetic field gradient measurement device comprises a gradiometer main body, a supporting base and a signal connection interface, wherein the gradiometer main body is used for measuring full-tensor magnetic field and magnetic field gradient information of each point in a space, and the full-tensor magnetic field and magnetic field gradient information comprises a response gradient value corresponding to five independent components in a full-tensor matrix and three magnetic field vector values of a central point; the supporting base is used for horizontal regulation operation which is required to be carried out during measurement of the magnetic field gradient of the space; the signal connection interface is used for transmitting weak voltage signals corresponding to the magnetic field gradient and central magnetic field intensity. According to the copper coil-based full-tensor magnetic field gradient measurement device provided by the invention, the technical defect that a traditional magnetic field gradient measurement device just can be used for measuring gradient information in a single direction of a magnetic field is solved, and the space consistency and the information integrity of magnetic field component measurement are increased.

The invention relates to a three-dimensional game engine scene pattern design method and system. The method comprises steps that space processing on a scene pattern is carried out, including unfolding the scene pattern through utilizing a space hierarchy structure and/or a space tree structure, nodes of the space rendering structure and/or the space tree structure are respectively introduced to a coordinate system of a present sub tree, moreover, corresponding conversion operation and a bounding volume are maintained by the nodes; a rendering state of the scene pattern is processed, a latent object visible set is constructed, post-processing operation is employed, ordering operation is carried out for the visual set according to the rendering state, and elimination operation and drafting operation are separated. The method is advantaged in that a scene system development period is shortened, code maintainability and reusability can be enhanced, game experience and presentation are enhanced, plenty-of-scene object drafting efficiency is improved, space consistency is considered, and rendering efficiency is improved.