机动目标航迹分段识别是判断目标行为意图的基础，然而现有航迹分段算法对模式变化检测能力弱，难以满足机动目标航迹快速精细化分段的需求。提出双层精细化航迹分段框架，预分段层检测目标运动过程中的模式切换，确定模式变化明显的预分段区，得到目标模式变化明显区域的预分段点；再分段层对模型差异小的非预分段区航迹进行回溯迭代优化再分段，得到更为精细的分段点。该框架具有从粗到精的航迹分段处理能力，实现了对于机动目标航迹的精细化分段识别。选取两个典型的目标机动仿真场景验证了所提算法的有效性，不仅减少了迭代优化时间，而且提高了分段识别精度。
Segment recognition of the maneuvering target track is the basis for judging the intention of target's behavior. However, existing track segmentation algorithms have a weak ability to detect changes of pattern, and are thus difficult to meet the requirement of fast and refined track segmentation for maneuvering targets. To this end, our paper proposes a two-layer refined track segmentation framework. The pre-segmentation layer is used to detect the pattern switching during the movement of the target, so as to determine the pre-segment area with obvious pattern changes and obtain the pre-segment points of the area with obvious target pattern changes. Then, iterative backtracking optimization is used to segment the track of the non-pre-segmented area with small differences, so as to obtain more refined segmentation points. The framework has the ability to process the track from coarse to fine segmentation, and can realize the recognition of refined segment of the maneuvering target track. Finally, the simulation results of two typical target maneuvering scenarios are given to demonstrate the effectiveness of our proposed method, which can not only reduce the time of iterative optimization, but also improve segmentation accuracy.
[1] 王萌萌,张曙光.基于模型预测静态规划的自适应轨迹跟踪算法[J]. 航空学报, 2018, 39(9):322105. WANG M M, ZHANG S G. Adaptive trajectory tracking algorithm based on tracking model predictive static programming[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(9):322105(in Chinese).
[2] ZHANG D Z, LEE K, LEE I. Hierarchical trajectory clustering for spatio-temporal periodic pattern mining[J]. Expert Systems with Application, 2018, 92:1-11.
[3] GAO C, ZHANG Z, HUANG C, et al. Semantic trajectory representation and retrieval via hierarchical embedding[J]. Information Sciences, 2020, 538:176-192.
[4] ZHANG D Z, LEE K, LEE I. Semantic periodic pattern mining from Spatio-temporal trajectories[J]. Information Sciences, 2019, 502:164-189.
[5] GENG Z Q, CHEN G F, HAN Y M, et al. Semantic relation extraction using sequential and tree-structured LSTM with attention[J]. Information Sciences, 2019, 509:183-192.
[6] ZHANG D, LEE K, LEE I. Mining hierarchical semantic periodic patterns from GPS-collected Spatio-temporal trajectories[J]. Expert Systems with Applications, 2018, 122:85-101.
[7] LIU L, WANG S, SU G, et al. A framework of mining semantic-based probabilistic event relations for complex activity recognition[J]. Information Sciences, 2017, 418:13-33.
[8] SHEU H T, HU W C. Multiprimitive segmentation of planar curves-A two-level breakpoint classification and tuning approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21:791-797.
[9] PITTMAN J, MURTHY C A. Fitting optimal piecewise linear functions using genetic algorithms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22:701-718.
[10] LINDER S P, SCHELL C. A non-Bayesian segmenting tracker for highly maneuvering targets[J]. IEEE Transactions on Aerospace & Electronic Systems, 2005, 41(4):1168-1177.
[11] 李亚军, 胡革, 宋文彬. 分段跟踪识别器的多特征加权指标设计[J]. 电讯技术, 2018, 58(11):1284-1289. LI Y J, HU G, SONG W B. Multi-feature weighted index design of segmentation track identifier[J]. Telecommunication Engineering, 2018, 58(11):1284-1289(in Chinese).
[12] LI X R, JILKOV V P. Survey of maneuvering target tracking. Part I. Dynamic models[J]. IEEE Transactions on Aerospace & Electronic Systems, 2004, 39(4):1333-1364.
[13] FRENCL V B, DO VAL J B R. Tracking with range rate measurements:Turn rate estimation and particle filtering[C]//Radar Conference. Piscataway:IEEE Press, 2012:287-292.
[14] ROTH M, HENDEBY G, GUSTAFSSON F. EKF/UKF maneuvering target tracking using coordinated turn models with polar/Cartesian velocity[C]//International Conference on Information Fusion. Piscataway:IEEE Press, 2014:1-8.
[15] ANDREAS L F, BREKKE E F. Rao-blackwellized particle filter for turn rate estimation[C]//Aerospace Conference. Piscataway:IEEE Press, 2017:1-7.
[16] YUAN X, HAN C, DUAN Z, et al. Adaptive turn rate estimation using range rate measurements[J]. IEEE Transactions on Aerospace & Electronic Systems, 2006, 42(4):1532-1541.
[17] LEE J G, HAN J, WHANG K Y. Trajectory clustering:A partition-and-group framework[C]//ACM SIGMOD International Conference on Management of Data. New York:ACM, 2007:593-604.
[18] PANAGIOTAKIS C, PELEKIS N, KOPANAKIS I, et al. Segmentation and sampling of moving object trajectories based on representativeness[J]. IEEE Transactions on Knowledge & Data Engineering, 2012, 24(7):1328-1343.
[19] BIZUP D F, BROWN D E. Maneuver detection using the radar range rate measurement[J]. IEEE Transactions on Aerospace & Electronic Systems, 2004, 40(1):330-336.
[20] 孙福明,吴秀清,王鹏伟. 转弯机动目标的两层交互多模型跟踪算法[J]. 控制理论与应用, 2008(2):233-236,241. SUN F M, WU X Q, WANG P W. Two-layer IMM tracking algorithm for turn maneuver[J]. Control Theory & Applications, 2008(2):233-236,241(in Chinese).
[21] ARASARATNAM I, HAYKIN S. Cubature Kalman filters[J]. IEEE Transactions on Automatic Control, 2009, 54(6):1254-1269.
[22] LIU J X, WANG Z L, XU M. DeepMTT:A deep learning maneuvering target-tracking algorithm based on bidirectional LSTM network[J]. Information Fusion, 2020, 53:289-304.
CJA