35results about How to "Improve the accuracy of association" patented technology

The invention discloses an adaptive distributed track data fusion method based on a covariance indicator function. The method comprises the following steps: 1) receiving and storing track data, and carrying out pretreatment on the received track data; 2) carrying out space-time registration on the multi-source track data; 3) associating the track data obtained by different sensors and determining correspondence relation between observation data and moving objects; and 4) carrying out fusion on the multi-source track data based on adaptive selection of fusion index, and determining motion state of each moving object. The method can selectively eliminate data having filtering divergence or overlarge system deviation and the like, which hinders improvement of precision of the fusion results, in the fusion process, and keeps the results having good consistency and carries out fusion.

An embodiment mode of the invention discloses an intuitionistic fuzzy association method for ADS-B monitoring data and radar tracks. The method comprises the steps of carrying out association pretreatment on the ADS-B monitoring data and radar tracks to obtain a plurality of primary association radar tracks, obtaining fuzzy intuitionistic indexes corresponding to association attributes between the ADS-B monitoring data and the primary radar tracks, obtaining fuzzy decision grades corresponding to the association attributes according to the fuzzy intuitionistic indexes, and carrying out weighing summation on the fuzzy intuitionistic indexes to obtain final associated radar tracks. The associated attributes comprise the distance, the speed, the speed difference and the course angle difference. The embodiment mode of the invention further discloses an intuitionistic fuzzy association device for the ADS-B monitoring data and the radar tracks. By means of the method, the intuitionistic fuzzy association method for the ADS-B monitoring data and the radar tracks can improve association accuracy between the ADS-B monitoring data and the radar tracks and is easy to achieve.

The invention discloses a nuclear K-mean value track correlation method based on KMDL criteria. The method comprises the following steps that firstly, a typical track correlation scene is established; secondly, the number of target tracks is determined based on the KMDL criteria; thirdly, the nuclear K-mean value algorithm is used for conducting correlation on the track observation scene. According to the nuclear K-mean value track correlation method based on the KMDL criteria, the KMDL criteria and the nuclear K-mean value algorithm are combined to solve the multi-target track correlation problem under the complex environment where clutters are dense, targets are near and the number of the targets is not known. According to the method, the movement state information of the targets is fully utilized, the correlation accuracy rate is effectively increased, the correlation criteria are simple and practicable, the calculated amount is small, the correlation accuracy rate is high, it is not sensitive for target intersection, and the method is suitable for track correlation under the environment where the targets are dense and intersect and applicable to engineering realization.

An SLAM data association method based on fuzzy-self-adaption is disclosed and a fuzzy-self-adaptive data association method based on an error ellipse and an associated threshold value is provided for the deficiencies of an existing SLAM data association method. According to the SLAM data association method, a fuzzy logic rule is applied to data association of a feature observation value and an estimation value, and the threshold value can be adaptively determined according to variations of the environment and noises, so that the data association effect is improved; and in order to effectively prevent a false road sign, a minimum road sign interval in the environment is tracked according to observation data, one, serving as a new virtual road sign, of two observation road signs with a shortest Euclidean distance is added in a system taste, and in addition, data association is carried out on the other observation quantity and the virtual road sign by virtue of the fuzzy rule. A simulation experiment and a real experiment prove that the SLAM data association method is capable of solving the data association problem and well adapting to the variations of the environment and the noises, so that the virtual road sign is effectively prevented and the observation loss rate is reduced.

The invention discloses an SLAM (Simultaneous Localization and Mapping) data association method based on maximum-minimum ant system optimization. The SLAM data association method based on maximum-minimum ant system optimization includes the steps: utilizing examination threshold filtering to reduce the solution space range associated with data, and improving the search efficiency of an algorithm; converting a data association problem into an optimal path solution problem, and utilizing an explanation tree model to stand for an association path node; and combining a maximum-minimum ant system with a combination maximum likelihood criterion, and taking a combination maximum likelihood value assumed by data association as a target function to perform path search. The SLAM data association method based on maximum-minimum ant system optimization reduces the association solution space of data association, can improve the search efficiency of the algorithm, and can effectively make up the defect that the ant colony algorithm is low in the rate of convergence, and stagnates in search and is easy to fall into local optimum.

The invention discloses a heterogeneous sensor combined track association and tracking method, which comprises the steps of S1, initializing system parameters; S2, mapping a plurality of data sourcesto a unified Cartesian coordinate system through Gauss Kruger projection; S3, performing coarse association on the data source message through hash coding; S4, performing Kalman filtering processing on the message track; S5, performing time alignment on the filtered message trace points through linear extrapolation and interpolation; S6, carrying out trace point association through a nearest neighbor algorithm; and S7, carrying out track association through a (M, C)/N logic judgment criterion. The method has the advantages of low calculation complexity, high association accuracy and the like.

The invention relates to a ship target track association method for a stationary orbit staring satellite remote sensing image, belongs to the technical field of satellite remote sensing, introduces ship automatic identification system information, firstly realizes association of cooperative ship targets, effectively reduces the number of association matching combinations, and then is divided into two association stages to associate non-cooperative targets. The number of matching combinations in the association algorithm is reduced, the ship target track association speed is improved, the influence of medium-low resolution and low frame rate conditions on interrupted track association of the ship target is overcome, association complexity is reduced, association accuracy is improved, finally, the associated interrupted tracks are connected, and ship target track association efficiency is improved; and integrity of ship target situation display is improved.

The present invention belongs to the technical field of radars or similar systems special for application, and discloses a lag track correlative fusion method, system and application based on a randomdistance. The concrete flows of the method comprise: inputting a first-class reference track and multiple other-class tracks; selecting windows with sizes of n; calculating the lag correlation; finding a track set meeting the correlation threshold value; performing verification of the random distance for the track correlation in the set; determining the correlative track and performing track fusion; and calculating the incidence relation between the tracks with lag correlation, ranking the incidence relation, finding the track with the maximum incidence relation and taking the track with themaximum incidence relation as an correlative track, and employing a least square method to start fusion from the track lag moment. The lag track correlative fusion method, system and application basedon the random distance are high in classification precision and low in operation time complexity, can effectively solve the fusion problem of lag and interrupted tracks in the track correlation fusion, can improve the track correlation correction and effectively improve the integration of target feature portrayal description through fusion.

The invention belongs to the field of data association, and particularly relates to a line feature data association method of a robot based on improved ant colony optimization. The method comprises the following steps: constructing a global coordinate system and a local coordinate system, and setting a sensor working mode; establishing a line feature observation model; extracting environmental line features using an improved segmentation-aggregation method; designing a line feature data association method combining an improved ICNN method and an improved ant colony optimization method; and inputting the environmental line feature information and the mobile robot pose information obtained by the sensor into a line feature data association method based on improved ant colony optimization, carrying out data association to obtain an association pair set, and updating the map feature set. Firstly, environment line characteristics are extracted based on laser sensor data, then an improved ICNN algorithm and an improved ant colony optimization algorithm are combined, the correlation accuracy of a data correlation algorithm is improved, and an accurate environment map is obtained.

The invention belongs to the data association field and especially relates to a mismatching determination method of indoor environment robot line characteristic ICNN data association. The invention provides an improved ICNN data association method of a decision rule of mismatching and mismatching prevention based on a line segment position relationship. The method is characterized by extracting anenvironmental line characteristic based on laser sensor data, re-selecting a line characteristic parameter, and summarizing line segment position relationships in a same two-dimensional plane; and for a problem that mismatching is easy to generate during line segment parallel or collineation, giving a mismatching evaluation model; and based on that, providing an improved ICNN algorithm. In the improved algorithm, computational time similar to the time of a standard algorithm is used to achieve higher correlation accuracy.

The invention relates to an active and passive track motion feature association method based on sequential processing. For the problems that an existing association method lacks effective and accurateestimation of statistical information of a heterogeneous sensor and lacks a reliable cleaning means for a to-be-associated track, so that the existing active and passive association based on the target motion feature has the problems of high association error rate, high processing resource consumption and the like, the invention provides an active and passive track motion feature association method based on sequential processing, and efficient association of massive observation tracks is completed; and the method comprises the specific steps of sector track traversal pairing, nearest neighbortime extrapolation registration, active sensor target motion feature statistical property estimation, passive sensor target motion feature statistical property estimation and association judgment based on motion feature association, and therefore, the requirement for high-reliability association application of mass observation data in a complex detection environment is met.

The invention provides a graph matching association method and system for multi-radar dense targets. The method comprises the following steps: constructing a vector set formed by radar tracking targets; analyzing the influence of errors on approximate congruency, and forming a vector similarity matrix; giving a single-moment graph matching algorithm calculation process, and determining a triangle with the highest approximate congruency as an alternative triangle in a vector similarity matrix by using a greedy algorithm; the vertexes and the basic edges are screened from other targets to form alternative associated triangles; and designing an association relationship maintaining method under continuous moments, judging successfully associated triangles at historical moments and current moments by using a DS evidence theory, and determining a target corresponding to a final successfully associated triangle at the current moment, so that the association relationship maintaining stability and the association accuracy are improved. The method has the advantages of being low in time complexity, high in convergence speed and high in real-time performance, and applications such as multi-radar target fusion track generation can be effectively supported by establishing the stable and correct target incidence relation.

The invention belongs to the technical field of sonar, provides a shell sonar and towed linear array sonar target track association method, and aims to solve the problem that the target track association performance is easy to decline due to the fact that the shell sonar and the towed linear array sonar are large in direction finding precision characteristic difference and only board angle similarity is adopted for target track association. According to the method, multi-dimensional features such as the side angle, the signal-to-noise ratio and the DEMON spectrum of the target are extracted, joint association processing is carried out, the robustness of target track association of the shell sonar and the towed linear array sonar can be effectively improved, and the association accuracy is improved.

The invention provides an SLAM data association method based on a self-adaptive local and grouping association strategy. The method comprises the following specific steps: firstly, adaptively determining a local data association region according to the position of the mobile robot at the current moment, the measurement range of a sensor and the distribution condition of observation values at the current moment; secondly, adaptively determining the grouping number of the observation values according to the local association region and the number and distribution of the current observation values, and grouping the current observation values by using a Gaussian mixture clustering algorithm on the basis of the grouping number; thirdly, completing data association between the observed value ineach group and the feature points in the local area by using a joint compatible branch and bound algorithm, and screening out an optimal association solution of each group; and finally, integrating each group of optimal solutions to obtain a final data association result. Experimental results prove that the method can reduce the association calculation amount while ensuring high association accuracy.