Search

CN-116361354-B - Interrupt track association method and device, storage medium and electronic equipment

CN116361354BCN 116361354 BCN116361354 BCN 116361354BCN-116361354-B

Abstract

The application relates to an interrupted track association method, an interrupted track association device, a storage medium and electronic equipment, wherein the method comprises the steps of obtaining a track before interruption and a track after interruption; the method comprises the steps of extracting at least one target point position information from a track before interruption, extracting at least one target point position information from a track after interruption to obtain a point position information sequence, determining point position characteristic information corresponding to each target point position information, determining target characteristic information corresponding to each target point position information in the point position information sequence and related to other target point position information in the point position information sequence according to the point position characteristic information corresponding to each target point position information, and associating the track before interruption with the track after interruption according to the target characteristic information corresponding to each target point position information. Therefore, the method and the device can carry out the interruption track association based on the association characteristics of the track before interruption and the track after interruption, do not need to carry out complex calculation on track data, and can adapt to the environment, thereby improving the accuracy of the interruption track association.

Inventors

  • WANG YUJIE
  • WU FEI
  • FANG SIAN

Assignees

  • 合肥讯飞数码科技有限公司

Dates

Publication Date
20260512
Application Date
20230119

Claims (8)

  1. 1. An interrupt track association method, comprising: acquiring a track before interruption and a track after interruption; Extracting at least one target point location information from the track before interruption, and extracting at least one target point location information from the track after interruption to obtain a point location information sequence comprising a plurality of target point location information; Determining point location feature information corresponding to each piece of target point location information in the point location information sequence; Determining target feature information corresponding to each target point location information in the point location information sequence and related to other target point location information in the point location information sequence according to the point location feature information corresponding to each target point location information in the point location information sequence, wherein the step of determining target feature information corresponding to each target point location information in the point location information sequence and related to other target point location information in the point location information sequence according to the point location feature information corresponding to each target point location information in the point location information sequence comprises the steps of inputting the point location feature information corresponding to each target point location information in the point location information sequence into a trained attention mechanism model for processing so as to obtain target feature information corresponding to each target point location information in the point location information sequence and related to other target point location information in the point location information sequence; The method comprises the steps of inputting the target characteristic information corresponding to each target point position information in the point position information sequence into a trained classification model to obtain a classification result, wherein the classification result is used for indicating whether the pre-interrupt track and the post-interrupt track are associated or not, and when the classification result indicates that the pre-interrupt track and the post-interrupt track are associated, the pre-interrupt track and the post-interrupt track are associated.
  2. 2. The method of claim 1, wherein the step of determining the point location feature information corresponding to each of the target point location information in the point location information sequence includes: Discretizing each target point location information in the point location information sequence to obtain corresponding discretized point location information; And determining point location characteristic information corresponding to each target point location information in the point location information sequence according to the discretization point location information.
  3. 3. The method of claim 2, wherein the target point location information includes continuous variable data of a point location longitude and continuous variable data of a point location latitude, and the step of discretizing each of the target point location information in the point location information sequence to obtain corresponding discretized point location information includes: Performing degree/minute/second conversion on the continuous variable data of the point location longitude and the continuous variable data of the point location latitude included in each target point location information in the point location information sequence to obtain corresponding whole degree part data, graduation part data and second degree part data of the point location longitude, and whole degree part data, graduation part data and second degree part data of the point location latitude; And rounding the second degree part data to obtain rounded second degree part data, and obtaining discretized point location information comprising the whole degree part data, the indexing part data and the rounded second degree part data.
  4. 4. The method of claim 2, wherein the target point location information includes continuous variable data of a point location speed and continuous variable data of a point location heading, and the step of discretizing each of the target point location information in the point location information sequence to obtain corresponding discretized point location information includes: and rounding the continuous variable data of the point location navigational speed and the continuous variable data of the point location navigational direction included in each piece of target point location information in the point location information sequence to obtain corresponding rounded point location navigational speed data and rounded point location navigational data, and obtaining discretized point location information comprising the rounded point location navigational speed data and the rounded point location navigational data.
  5. 5. The method of claim 2, wherein the step of determining, from the discretized point location information, point location feature information corresponding to each of the target point location information in the point location information sequence includes: And carrying out coding processing on the discretized point location information corresponding to each target point location information in the point location information sequence to obtain corresponding point location characteristic information.
  6. 6. An interrupt track association device, comprising: the acquisition module is used for acquiring the track before interruption and the track after interruption; The extraction module is used for extracting at least one target point location information from the track before interruption and extracting at least one target point location information from the track after interruption so as to obtain a point location information sequence comprising a plurality of target point location information; The first determining module is used for determining point location characteristic information corresponding to each piece of target point location information in the point location information sequence; The second determining module is used for determining target feature information corresponding to each target point location information in the point location information sequence and related to other target point location information in the point location information sequence according to the point location feature information corresponding to each target point location information in the point location information sequence, wherein the second determining module is specifically used for inputting the point location feature information corresponding to each target point location information in the point location information sequence into a trained attention mechanism model for processing so as to obtain target feature information corresponding to each target point location information in the point location information sequence and related to other target point location information in the point location information sequence; The system comprises a point location information sequence, a correlation module and a correlation unit, wherein the point location information sequence is used for storing target characteristic information corresponding to the target point location information, the correlation module is used for correlating the pre-interruption track with the post-interruption track according to the target characteristic information corresponding to the target point location information in the point location information sequence, the input unit is used for inputting the target characteristic information corresponding to the target point location information in the point location information sequence into a trained classification model to obtain a classification result, the classification result is used for indicating whether the pre-interruption track is correlated with the post-interruption track or not, and the correlation unit is used for correlating the pre-interruption track with the post-interruption track when the classification result indicates that the pre-interruption track is correlated with the post-interruption track.
  7. 7. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program adapted to be loaded by a processor for performing the steps of the interrupt track association method according to any of claims 1-5.
  8. 8. An electronic device comprising a memory in which a computer program is stored and a processor that performs the steps in the interrupt trail association method of any one of claims 1-5 by invoking the computer program stored in the memory.

Description

Interrupt track association method and device, storage medium and electronic equipment Technical Field The present application relates to the field of computer technologies, and in particular, to a method and apparatus for associating an interrupt track, a storage medium, and an electronic device. Background In the field of radar data processing, tasks such as target tracking, situation awareness, information fusion and the like are particularly dependent on track segment association, and if a track is interrupted, the tasks can be affected very badly, so that huge losses are caused. There are many reasons for causing the track break, such as high-speed maneuvering of the target, intentional stopping of the target, low probability of detection by the sensor, long sampling interval of the sensor, clutter, electromagnetic interference, and the like. The existing interrupt track association schemes mainly comprise two types, namely, track prediction is carried out by depending on track information before interrupt, then feature similarity calculation is constructed on the predicted track and the newly obtained track information, and the second type is that feature similarity calculation is directly carried out on features before track interrupt and the newly obtained track. However, the first approach to track interruption is severely dependent on the accuracy of track prediction, and cannot predict the track very accurately due to the mobility of the target, errors of the measuring tool, etc., especially the track prediction based on kalman filtering, and once new heading information is lacking, the track cannot be predicted. The second method for interrupting the track is mainly to construct the behavior characteristics of the target and analyze the behavior characteristics before and after the track interruption to calculate the track similarity, and because of the diversity of the scenes of the target and the difficulty in generalizing the characteristics, the similarity calculation result is not accurate enough, and the interrupted track cannot be accurately associated. Thus, the accuracy of existing outage track association schemes is to be improved. Disclosure of Invention The application aims to provide an interrupted track association method, an interrupted track association device, a storage medium and electronic equipment, so as to improve the accuracy of interrupted track association. The embodiment of the application provides an interrupted track association method, which comprises the following steps: acquiring a track before interruption and a track after interruption; Extracting at least one target point location information from the track before interruption and extracting at least one target point location information from the track after interruption to obtain a point location information sequence comprising a plurality of target point location information; Determining point location characteristic information corresponding to each target point location information in the point location information sequence; According to the point location feature information corresponding to each target point location information in the point location information sequence, determining target feature information corresponding to each target point location information in the point location information sequence and related to other target point location information in the point location information sequence; And associating the track before interruption with the track after interruption according to the target characteristic information corresponding to each target point position information in the point position information sequence. The embodiment of the application also provides an interrupted track association device, which comprises: the acquisition module is used for acquiring the track before interruption and the track after interruption; The extraction module is used for extracting at least one target point location information from the track before interruption and extracting at least one target point location information from the track after interruption so as to obtain a point location information sequence comprising a plurality of target point location information; The first determining module is used for determining point location characteristic information corresponding to each target point location information in the point location information sequence; The second determining module is used for determining target characteristic information corresponding to each target point position information in the point position information sequence and related to other target point position information in the point position information sequence according to the point position characteristic information corresponding to each target point position information in the point position information sequence; And the association module is used for associating the track before interruption and the track after interru