25 results about "Track initiation" patented technology

The application relates to a kind of millimeter wave radar multi-vehicle tracking methods based on traffic scene, comprising: the original echo data of millimeter wave radar is preprocessed, and a plurality of frames of point cloud data are obtained;Each frame of point cloud data is clustered using a hierarchical clustering algorithm based on target information;Rectangular association wave door is set in combination with standard lane width and safe following distance, and the rectangular association wave door is corrected according to the historical information obtained by target tracking;All target centroid points in the corrected rectangular association wave door are fused according to probability;The existing track associated with the equivalent centroid point and the existing track not associated with the equivalent centroid point are updated, and a plurality of updated tracks are obtained;For the target centroid point not assigned to the existing track, the logical method is used for track initiation, and a plurality of stable starting tracks are obtained;The target tracking track is obtained by managing the track. The method combines the characteristics of radar measurement distribution and motion mode of vehicle target, and realizes the robust tracking of multi-vehicle target.

A sea surface target classification method based on multi-motion feature fusion is characterized by comprising the steps that a double-station high-frequency radar is adopted to invert a sea surface vector flow field and a wind field, and quality control and high-precision interpolation are carried out on the flow field and the wind field; simulating a drifting target track by adopting a kinetic equation, and extracting an artificial power target track by adopting radar detection, including target detection, false alarm suppression, track initiation, tracking filtering and track termination; extracting motion features of the target from the track data, including a speed feature, an acceleration feature, a course feature, a steering rate feature and a track curvature feature, and constructing a motion feature data set; and designing the architecture of the multi-channel deep convolutional neural network, training the network weight, and identifying an artificial power target and a drifting target.

The present invention provides a sea surface target tracking method based on real-time estimation of detection accuracy, which determines the single-shot target range accuracy σ of the radar. R Determine the single-shot angular accuracy σ of the radar. A According to the single measurement target distance accuracy σ R and single-detection angle measurement accuracy σ A A Gaussian distribution model is constructed; the radar's current measurement parameters of the target are obtained and input into the Gaussian distribution model to determine the range of range and angle accuracy under different probabilities of the current detection result. The measurement parameters include at least the target's range accuracy, size, and signal-to-noise ratio. The target's association threshold is updated in real time based on the accuracy range of angle and range. The trajectory initiation strategy is updated based on the updated association threshold. This enables rapid initiation or rapid convergence of the target trajectory. Furthermore, during the multi-hypothesis branch selection process, branches with high-precision measurement initiation are prioritized for output, improving the speed and accuracy of branch switching.

The present invention belongs to the technical field of multi-target tracking, and specifically relates to an adaptive track initiation method based on GLMB. The present invention traverses all possible tracks based on measurement data at two consecutive moments, and preliminarily screens the measurement data to remove most clutter using speed screening rules and Doppler information screening rules. The target measurement probability is calculated based on the posterior probability to distinguish the measurement source. The target measurement probability can be used to distinguish whether the measurement originates from a new target or a surviving target. The speed information implicit in the Doppler measurement is used to calculate the initial operating state of the new target and enter the next prediction process, thereby completing the track initiation function.

The application relates to a multi-element track initiation method and system based on a modified Hough transform, and belongs to the technical field of radar information processing. The method comprises the following steps: acquiring all point tracks after point track condensation, selecting three continuous measurement data in a period, performing one-by-one traversal correlation to obtain a to-be-determined track; setting a multi-element constraint condition, screening the to-be-determined track based on the multi-element constraint condition, and retaining the to-be-determined track meeting the screening requirement; removing the to-be-determined tracks that are not collinear based on the Hough transform to obtain the to-be-determined tracks of approximate straight lines in a three-dimensional space; evaluating the confidence degree of track initiation based on the signal-to-noise ratio of the track, determining the track meeting the signal-to-noise ratio threshold condition as an effective track, taking the effective track as a final output, and completing track initiation. On the basis of effectively suppressing false tracks, the application improves the rapid track initiation capability of a target, and simultaneously avoids the problems of large calculation amount and poor real-time performance of a traditional Hough transform algorithm.

The invention relates to the technical field of radar data processing, in particular to a group initiation method based on cyclic random Hough transformation and DBSCAN (Density-Based Spatial Clustering of Applications with Noise), which comprises the following steps of: S1, acquiring a set of adjacent three frames of echo trace points of a radar, and executing random Hough transformation on the first two frames of trace points in the set of the adjacent three frames of echo trace points to form a characteristic parameter matrix; s2, performing dimension accumulation and Gaussian convolution condensation on the characteristic parameter matrix, extracting trace points corresponding to peak values according to a condensation result to form a temporary group, and updating a trace point set; and S3, performing DBSCAN spatial clustering on the temporary group to obtain a clustering result, and performing group track confirmation on the clustering result through a third frame echo point. The method not only can solve the problem of track initiation of the dense group, but also has relatively high clutter resistance, is small in calculation amount, and has relatively high engineering application value.

The present invention discloses a pure angle target tracking method suitable for non-uniformly spaced detection equipment. The method mainly includes the following steps: S1, initializing the target tracking system; S2, initiating the target tracking system's track; S3, calculating the target angular velocity information of the established track; S4, associating and maintaining the track; S5, determining candidate targets and updating the track; and S6, outputting the current track. The present invention can adapt to pure angle tracking under different target angle variations.

The application discloses a kind of synchronous satellite radar track initiation methods based on sky-wave gate correction, belong to the technical field of target tracking in radar data processing.This application is aimed at the problem of a large number of false tracks in track initiation in the target tracking of synchronous satellite radar.It includes establishing north-east sky right-angle coordinate system with sky-wave over-the-horizon radar receiving station as origin, determining the coordinates of synchronous satellite radar transmitting station, synchronous satellite radar receiving station and all measurement points in track initiation period;Determining the track tracking information of sky-wave over-the-horizon radar;According to the track information and state error of sky-wave over-the-horizon radar, establish the tracking gate of sky-wave over-the-horizon radar;Then, based on the traditional logical initiation method, establish the annular initiation gate of synchronous satellite radar;Finally, take the intersection of the annular gate of synchronous satellite radar and the tracking gate of sky-wave over-the-horizon radar as the correction gate of synchronous satellite radar, and perform track initiation, i.e.The starting track of synchronous satellite radar can be obtained.The application is suitable for track initiation in target tracking.

The invention belongs to the technical field of target detection and tracking, and particularly relates to a multi-target detection and tracking method based on distance-azimuth measurement under a noise background, which is characterized by comprising the following steps of: acquiring a radar echo signal; processing the radar echo data of each target point by using a two-dimensional unit average constant false alarm detection algorithm, and extracting a potential target trace point; carrying out track initiation and initialization on the detected target trace point, and forming a possible target track; associating the target trace point of the current frame with an existing target track; a target state equation of a target point and a distance-orientation-based measurement equation are established based on a uniform-speed motion model, a Kalman filter is used for carrying out state estimation and prediction on the associated target track, the optimal estimation state of the target is output, and finally a stable target tracking track is formed. The invention also provides a multi-target detection and tracking system based on distance-azimuth measurement under the noise background.

The present invention discloses a track initiation method based on batch processing, comprising the following steps: 1: agglomerating measurement points within a scanning cycle; 2: selecting measurement points for calculating characteristic parameters in combination with target motion characteristics; 3: classifying the measurement points according to the target motion characteristics, and creating a characteristic parameter linked list for each of them; 4: transforming the characteristic parameter information of the measurement points filtered in step 2, projecting the information onto a velocity-coordinate parameter space of a reference frame, and serving as point track data in the parameter space; 5: repeating steps 2 to 4, traversing the scanning cycle, and clustering the point track data in the parameter space using a DBSCAN algorithm; 6: obtaining the centroid of the clusters formed by clustering in the parameter space, and serving as the characteristic information of the target corresponding to the cluster; and 7: inferring the coordinate information of the target in each scanning cycle based on the characteristic information of the target, thereby completing track initiation.

This invention relates to the field of air traffic control technology, providing a method and apparatus for fusion of point tracks from primary and secondary combined air traffic control radars. The apparatus includes a data communication module, a software operation management module, a point track preprocessing module, a point track fusion module, a track preprocessing module, a track fusion module, a track initiation and track correlation module, a motion model library, a track filtering and prediction module, a special area processing module, a special track processing module, and an intelligence output module. This invention can effectively realize data fusion processing of primary and secondary combined air traffic control radars, achieving primary air traffic control radar data processing, secondary air traffic control radar data processing, primary and secondary combined radar point track fusion processing, and primary and secondary combined radar track fusion processing, thereby improving the aircraft surveillance intelligence fusion capability.

The invention discloses an auxiliary track method and device for a dense scene, a vehicle and a storage medium. The method comprises the following steps: acquiring current target detection data of a vehicle-mounted radar; based on the current target detection data, analyzing the distribution information of the current detection target in each detection sub-region of the current detection region of the vehicle-mounted radar; based on the distribution information of each current detection target, judging whether the number of target detection regions in each detection sub-region is greater than a preset threshold value or not; wherein the target detection area means that the detection sub-areas, the number of the current detection targets of which meets a preset number, exist in a substitution area; when the number of the target detection areas is greater than a preset threshold value, optimizing a track starting condition and track updating of the current detection target based on the distribution information of each current detection target; wherein the track starting condition of the current detection target is a condition for determining stable starting of the track.

The application discloses a false track identification method based on a deep neural network, and through the method, false tracks can be effectively inhibited in a dense clutter environment. Specifically, the method can be used in a track starting stage to identify false tracks of new-born tracks and replace traditional rule judgment, thereby effectively improving false information and missing information of target information. On the other hand, the method can be used in a track maintaining stage to identify the updating state of target tracks in real time, quickly find the correlation error between target tracks and radar measurements, timely correct the correct target measurements, and improve the stability of target tracks. Through the above two aspects, false tracks can be effectively removed in the clutter environment, and stable and reliable target information can be obtained.

The present invention discloses a track initiation method based on a combination of rules and FasterRCNN models, which includes the following steps: obtaining radar echo information at N consecutive moments; generating a radar echo image according to the radar echo information; detecting the radar echo image using FasterRCNN to obtain a number of candidate areas; performing angle constraint judgment and filter prediction judgment on the echo point information in each candidate area in turn to obtain track initiation information; generating a radar echo image according to the radar echo information, and then detecting the radar echo image in combination with FasterRCNN, and utilizing the image processing capability of FasterRCNN to effectively extract candidate frames where tracks may exist; finally screening the candidate frames by combining angle constraint and filter prediction judgment, taking into account the advantages of sequential processing and batch processing methods, thereby reducing the false start rate and improving the performance of target track initiation.

The invention provides an intelligent track initiation method based on a dual-channel depth Q learning model, and the method comprises the steps: setting logic method M and N parameter initial values for track initiation, carrying out the track initiation, and determining a region-of-interest sequence; standardizing the radar video region-of-interest signal sequence; constructing a dual-channel MN parameter optimization neural network model; training a dual-channel MN parameter optimization neural network model by using a deep Q learning method; and obtaining optimized M and N parameters by utilizing the optimized quantity of the obtained M and N parameters after training, and starting the track by utilizing the optimized M and N parameters by using a logic method. The features of the radar video signal and the track initiation information are synchronously extracted by using the deep neural network, the information of the radar signal is fully utilized, and the track initiation performance is effectively improved.

The application discloses a centralized MIMO radar multi-target tracking robust power allocation method for low interception, which comprises the following steps: a centralized MIMO radar working in a simultaneous multi-beam mode is adopted to track multiple targets dispersedly distributed in a monitoring area; a total interception probability of the centralized MIMO radar system by an enemy target formation is derived as a low interception performance representation index according to a representation index of target tracking accuracy; a centralized MIMO radar multi-target tracking robust power allocation optimization model for low interception is established; and a three-step solving strategy based on an interior point method and a gradient projection method is adopted to solve the optimization model, so that a radiation power vector with optimal system performance is the optimal solution of the model. The application can effectively improve the multi-target tracking accuracy and the low interception performance in the track initiation stage and the case of insufficient resources, and effectively improves the system performance of the centralized MIMO radar.

The invention provides a track-video dual-mode Rainbow network-based track evaluation method, which is characterized by comprising the following steps of: extracting N track points in a track by a sliding window to form a track point sequence, and slicing a radar video by taking the position of each track point as a center to obtain a video slice sequence; preprocessing each track point and each video slice in the track point sequence and the video slice sequence; constructing a track-video bimodal neural network, and training a track-video bimodal neural network model by using a Rainbow reinforcement learning method; in the track starting and tracking stages, the trained track-video bimodal neural network model is used for evaluating and updating the track quality of each track after point track association, and the tracks with the track quality lower than a threshold value are removed. According to the method, the dual-channel deep neural network is established to synchronously analyze the radar video information and the track information, the features of a real target and a false target are effectively extracted, the track quality can be correctly evaluated, and the number of false tracks is reduced.

The invention relates to the technical field of track initiation, and discloses a tree-based track initiation method and electronic equipment. Comprising the following steps: S01, carrying out point-to-point correlation on a target trace point and a temporary track node, and formulating a correlation result; s02, related results are updated, and a temporary track tree to be processed is constructed; s03, identifying an initial node from the temporary track tree to be processed, and starting the initial node according to a track in sequence; s04, executing corresponding track processing operation on the temporary track tree to be processed; s05, carrying out structure adjustment on the temporary track tree to be processed; according to environment information sensed in real time, parameters in point-to-point association and track initiation confirmation can be adaptively optimized and adjusted, the problems of sensitive parameters, large calculation amount and poor non-linear adaptation existing when track initiation is carried out by depending on expert knowledge are avoided, the track initiation performance in a dynamic complex environment is improved, and the track initiation efficiency is improved. And accurate track initiation of the real target is ensured.

The invention discloses a cross-cloud broken-sequence formation small target continuous tracking method based on a pipeline belt, and the method comprises the steps: in the aspect of state estimation, in order to achieve the high-precision state estimation, based on a space-based detection link, obtaining a target intrinsic characteristic pipeline belt and a detection error pipeline belt through decoupling, and carrying out the tracking of the target intrinsic characteristic pipeline belt and the detection error pipeline belt. A target motion model is constructed based on the intrinsic characteristic pipeline belt to realize high-precision state prediction, and a detection error pipeline belt is used as a measurement error to realize stable state association; in the aspect of appearance modeling, a target is tracked based on observation noise and a target motion model, a track is calculated by using a formation multi-target fine track initiation algorithm, an adaptive correlation gate is constructed based on an intrinsic characteristic pipeline belt, and data association optimization is realized; a target tracking failure judgment mechanism is established for the cross-time phase matching problem of the cloud-penetrating broken-sequence weak and small formation targets, and if tracking fails, recapturing of breakpoint targets is realized by using a pyramid optical flow method and a hierarchical clustering method based on blocks, so that the tracking reliability is ensured.

The present invention relates to the field of millimeter-wave radars, and provides a method for measuring the initial track of a target. The method includes: establishing an initial area and dividing it to obtain a plurality of delimited areas; obtaining the radial velocity, position, and azimuth angle of each target within the delimited areas; obtaining the transverse velocity and longitudinal velocity corresponding to the target according to the radial velocity, the position, and the azimuth angle; and initiating the track of the target according to the transverse velocity, the longitudinal velocity, the position, and the azimuth angle. Through the method for measuring the initial track of a target provided by the present invention, the timely initiation of the target track is achieved.

The application provides a kind of intelligent track initiation method, utilizes early warning detection equipment m consecutive period measurement data, constructs directed graph, and sets node initial feature and edge feature;Track initiation network is composed of node generation network and node decision network, node generation network is based on the construction of Transform network, 1-hop subgraph is handled to the center of node, and the feature representation of node is output, node decision network is feedforward network, whether the connection between the true target corresponding to node and true target node exists is judged;Using historical measurement data, track initiation training data set is established, and loss function is determined, and track initiation network is optimized and trained;The track initiation network that has been trained is deployed, and the initial track of target is obtained by judging the size of output probability. The application provides a kind of unified, efficient target track initiation method, which can realize stable, rapid and accurate track initiation of target.

The invention discloses an improved track initiation method based on correction Hough transformation, and designs a method for filtering clutters first and then initiating the track in order to solve the problem that the false alarm rate of the track initiation is high in a strong clutter environment. The calculation amount of the algorithm is reduced by using a clutter filtering algorithm, clutters are few and relatively concentrated after clutter filtering, and a fine track initiation algorithm suitable for an environment with few clutters and relatively concentrated is designed, so that the calculation amount and storage space of a system occupied by track initiation are reduced as much as possible, and the track initiation efficiency is improved. And high-quality track initiation is ensured. The track initiation algorithm is provided.

The present invention discloses a common-aperture radar ESM joint tracking method for complex electromagnetic environments. The method includes: acquiring measurement combination information by setting different combination modes according to different situational scenarios; clustering measurement values ​​based on the measurement combination information and confidence levels to determine the secondary angle measurement clustering results; setting different initial track types based on the secondary angle measurement clustering results at the track initiation stage; pre-setting associated measurement types; and selecting different filtering methods or techniques based on the pre-set associated measurement types and track types during track association to determine the current angle and / or distance and velocity, and outputting the results. This method can effectively improve the stability and accuracy of target tracking and enhance the low-intercept performance of active phased array radar.

The application belongs to the technical field of radar signal back-end processing, and relates to a millimeter wave radar tracking method in a multi-target complex environment, which comprises the following steps: step one: processing a radio frequency signal received by a radar to generate millimeter wave radar point cloud data; step two: demarcating a radar action range, eliminating point cloud data beyond the range, and then performing point cloud clustering through a DBSCAN clustering method to obtain merge points; and step three: performing track initiation, matching measurement data with a track through data association gate judgment, updating a target state if successful association, and then outputting the track, or otherwise performing track loss or maintenance operation through a scoring board mechanism. The application can effectively improve the accuracy of target tracking, reduce the false tracking rate of multi-target tracking, reduce the calculation complexity of the algorithm, and greatly reduce the calculation time.