基于时空轨迹信息的目标行为模式在线分类方法

doi:10.7527/S1000-6893.2022.27281

Abstract

Abstract:

In the early warning and monitoring field， it is very important to predict target behavior patterns in time for situation cognition. Firstly， an Inductive Conformal Multi-class Predictor （ICMP） with outlier detection is proposed to solve the problem that most current classifiers are in low computational efficiency and not sensitive to outliers. Secondly， to overcome the problem that most behavior pattern classifiers only consider the spatial location information of the target and ignore the course and velocity information， a concept of Spatio-Temporal Hausdorff Distance （STHD） is proposed to distinguish behaviors with similar spatial position but different course and velocity effectively. Then， a Directed Spatiotemporal Hausdorff Nearest Neighbor Nonconformity Measure （DSHNN-NCM） function is constructed by combining the idea of KNN and STHD. On this basis， a Sequential Spatiotemporal Hausdorff Nearest Neighbor Inductive Conformal Multi-class Predictor （SSHNN-ICMP） with outlier detector is proposed， which can online learn and predict the frequent behaviors of targets in the early warning and monitoring scenario. Finally， experiments and analyses are carried out in a military simulation scenario and a real civilian scenario. The results show that the proposed algorithm has better accuracy and real-time performance， showing good applicability in early warning and surveillance tasks.

Key words: spatiotemporal trajectory, behavior pattern, Hausdorff distance, conformal predictor, online classification

CLC Number:

V355.1

Qiaowen JIANG, Yu LIU, Ziran DING, Shun SUN, Tao JIAN. Online classification of target behavior pattern based on spatiotemporal trajectory information[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(8): 327281-327281.

Figures/Tables 11

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Table 1

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Table 2

Fig. 9

References 29

1	何友，姚力波，江政杰. 基于空间信息网络的海洋目标监视分析与展望［J］. 通信学报， 2019， 40（4）： 1-9.
	HE Y， YAO L B， JIANG Z J. Summary and future development of marine target surveillance based on spatial information network［J］. Journal on Communications， 2019， 40（4）： 1-9 （in Chinese）.
2	何友，姚力波. 天基海洋目标信息感知与融合技术研究［J］. 武汉大学学报（信息科学版）， 2017， 42（11）： 1530-1536.
	HE Y， YAO L B. Space-based Sea target information awareness and fusion［J］. Geomatics and Information Science of Wuhan University， 2017， 42（11）： 1530-1536 （in Chinese）.
3	何友，熊伟，刘俊，等. 海上信息感知与融合研究进展及展望［J］. 火力与指挥控制， 2018， 43（6）： 1-10.
	HE Y， XIONG W， LIU J， et al. Review and prospect of research on maritime information perception and fusion［J］. Fire Control & Command Control， 2018， 43（6）： 1-10 （in Chinese）.
4	PAN X L， HE Y， WANG H P， et al. Mining regular behaviors based on multidimensional trajectories［J］. Expert Systems With Applications， 2016， 66： 106-113.
5	ANSARI M Y， MAINUDDIN， AHMAD A， et al. Spatiotemporal trajectory clustering： A clustering algorithm for spatiotemporal data［J］. Expert Systems With Applications， 2021， 178： 115048.
6	RONG H， TEIXEIRA A P， GUEDES SOARES C. Data mining approach to shipping route characterization and anomaly detection based on AIS data［J］. Ocean Engineering， 2020， 198： 106936.
7	潘奇明，周文辉，程咏梅. 运动目标轨迹分类与识别［J］. 火力与指挥控制， 2009， 34（11）： 79-83.
	PAN Q M， ZHOU W H， CHENG Y M. Trajectory classification and recognition of moving objects［J］. Fire Control & Command Control， 2009， 34（11）： 79-83 （in Chinese）.
8	魏龙翔，何小海，滕奇志，等. 结合Hausdorff距离和最长公共子序列的轨迹分类［J］. 电子与信息学报， 2013， 35（4）： 784-790.
	WEI L X， HE X H， TENG Q Z， et al. Trajectory classification based on Hausdorff distance and longest common SubSequence［J］. Journal of Electronics & Information Technology， 2013， 35（4）： 784-790 （in Chinese）.
9	曲琳，周凡，陈耀武. 基于Hausdorff距离的视觉监控轨迹分类算法［J］. 吉林大学学报（工学版）， 2009， 39（6）： 1618-1624.
	QU L， ZHOU F， CHEN Y W. Trajectory lcassification based on Hausdorff distance for visual surveillance system［J］. Journal of Jilin University （Engineering and Technology Edition）， 2009， 39（6）： 1618-1624 （in Chinese）.
10	POKORNY F T， HAWASLY M， RAMAMOORTHY S. Topological trajectory classification with filtrations of simplicial complexes and persistent homology［J］. International Journal of Robotics Research， 2016， 35（1-3）： 204-223.
11	BOLBOL A， CHENG T， TSAPAKIS I， et al. Inferring hybrid transportation modes from sparse GPS data using a moving window SVM classification［J］. Computers Environment and Urban Systems， 2012， 36（6）：526-537.
12	赵竹珺，吉根林. 时空轨迹分类研究进展［J］. 地球信息科学学报， 2017， 19（3）： 289-297.
	ZHAO Z J， JI G L. Research progress of spatial-temporal trajectory classification［J］. Journal of Geo-Information Science， 2017， 19（3）： 289-297 （in Chinese）.
13	潘新龙，程学旗，王海鹏，等. 基于航迹数据挖掘的目标行为分析概述［J］. 指挥与控制学报， 2021， 7（4）： 335-341.
	PAN X L， CHENG X Q， WANG H P， et al. An overview of target behavior analysis based on trajectory data mining［J］. Journal of Command and Control， 2021， 7（4）： 335-341 （in Chinese）.
14	曹卫权，李智翔，魏强，等. 基于区域分布概率密度估计的轨迹分类方法［J］. 计算机工程， 2018， 44（4）： 262-267， 286.
	CAO W Q， LI Z X， WEI Q， et al. Trajectory classification method based on probability density estimation of regional distribution［J］. Computer Engineering， 2018， 44（4）： 262-267， 286 （in Chinese）.
15	崔彤彤，王桂玲，高晶. 基于1DCNN-LSTM的船舶轨迹分类方法［J］. 计算机科学， 2020， 47（9）： 175-184.
	CUI T T， WANG G L， GAO J. Ship trajectory classification method based on 1DCNN-LSTM［J］. Computer Science， 2020， 47（9）： 175-184 （in Chinese）.
16	OWENS J， HUNTER A. Application of the self-organising map to trajectory classification［C］∥Proceedings Third IEEE International Workshop on Visual Surveillance. Piscataway： IEEE Press， 2002： 77-83.
17	BOLBOL A， CHENG T， TSAPAKIS I， et al. Inferring hybrid transportation modes from sparse GPS data using a moving window SVM classification［J］. Computers， Environment and Urban Systems， 2012， 36（6）： 526-537.
18	SAINI R， KUMAR P， ROY P P， et al. Modeling local and global behavior for trajectory classification using graph based algorithm［J］. Pattern Recognition Letters， 2021， 150（C）： 280-288.
19	PAN X L， WANG H P， HE Y， et al. Online classification of frequent behaviours based on multidimensional trajectories［J］. IET Radar， Sonar & Navigation， 2017， 11（7）： 1147-1154.
20	VOVK V， GAMMERMAN A， SHAFER G. Algorithmic Learning in a Random World［M］. Cham： Springer International Publishing， 2022.
21	VOVK V. Universal well-calibrated algorithm for on-line classification［C］∥Learning Theory and Kernel Machines. Berlin： Springer， 2003： 358-372.
22	PAPADOPOULOS H. Inductive conformal prediction： Theory and application to neural networks［M］∥Tools in Artificial Intelligence. London： InTech， 2008 .
23	LAXHAMMAR R， FALKMAN G. Online learning and sequential anomaly detection in trajectories［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2014， 36（6）： 1158-1173.
24	PAN X L， WANG H P， CHENG X Q， et al. Online detection of anomaly behaviors based on multidimensional trajectories［J］. Information Fusion， 2020， 58： 40-51.
25	AGRAWAL R， IMIELIŃSKI T， SWAMI A. Mining association rules between sets of items in large databases［C］∥Proceedings of the 1993 ACM SIGMOD international conference on Management of data. New York： ACM， 1993： 207-216.
26	LI H H， LIU J X， YANG Z L， et al. Adaptively constrained dynamic time warping for time series classification and clustering［J］. Information Sciences， 2020， 534： 97-116.
27	GAMMERMAN A， VOVK V. Hedging predictions in machine learning［J］. The Computer Journal， 2007， 50（2）： 151-163.
28	PICIARELLI C， MICHELONI C， FORESTI G L. Trajectory-based anomalous event detection［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2008， 18（11）： 1544-1554.
29	姜乔文，刘瑜，谭大宁，等. 时空轨迹多维特征融合的行为规律挖掘算法［J］. 航空学报， 2023， 44（5）： 326394.
	JIANG Q W， LIU Y， TAN D N， et al. Regular behaviors mining algorithm based on spatiotemporal trajectory multidi-mensional features fusion［J］. Acta Aeronautica et Astronautica Sinica， 2023， 44（5）： 32394 （in Chinese）.

算法		K	Precision/%	Recall/%	F1-score/%	Accuracy/%	FA/%	Time/s
CMC	HD-KNN	2	51.74	56.95	52.13	52.94		2 056.7
		3	52.96	57.13	53.04	53.68		2 061.9
		4	54.03	57.32	54.15	53.89		2 068.2
		5	54.01	57.26	54.03	53.73		2 075.6
	STDH-KNN	2	92.26	99.08	94.80	92.26		2 063.1
		3	92.38	99.36	95.12	92.42		2 069.4
		4	92.48	99.40	95.42	92.54		2 076.9
		5	92.41	99.46	95.37	92.43		2 086.5
SSHNN-ICMP		2	98.57	99.04	98.95	98.99	0.13	47.2
		3	99.13	99.31	99.28	99.36	0.05	47.7
		4	99.01	99.38	99.23	99.28	0.03	48.1
		5	99.03	99.40	99.21	99.22	0.02	48.8

算法		Precision/%	Recall/%	F1-score/%	Accuracy/%	FA/%	Time/s
CMC	HD-KNN	88.25	93.12	90.63	89.19		37 398.1
CMC	STDH-KNN	91.06	95.86	93.87	91.86		37 563.3
SSHNN-ICMP		95.71	95.03	95.33	95.92	0.51	217.6

[1]	Qiaowen JIANG, Yu LIU, Daning TAN, Shun SUN, Kai DONG. Regular behaviors mining algorithm based on fusion of multidimensional features of spatiotemporal trajectory [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 326394-326394.
[2]	ZHENG Yanhong, DENG Xiangjin, PANG Yong, JIN Shengyi, YAO Meng, ZHAO Zhihui. Research on classification of relative density in lunar regolith drilling [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(4): 223391-223391.
[3]	PAN Xinlong, WANG Haipeng, HE You, XIONG Wei, ZHOU Wei. Anomalous behavior detection method based on multidimensional trajectory characteristics [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2017, 38(4): 320442-320442.
[4]	FAN Chongqing, LYU Zhenzhou. Global sensitivity analysis method for multivariate output based on fuzzy Hausdorff distance [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2017, 38(10): 220870-220870.
[5]	WANG Huaxia, CHENG Yongmei, LIU Nan. A robust scene matching method for mountainous regions with illumination variation [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2017, 38(10): 321101-321101.
[6]	WANG Yue;MAO Shi-yi;CHEN Wei. A Multiresolution Algorithm for Image Registration with Partial Hausdorff Distance [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2004, 25(6): 593-597.

Online classification of target behavior pattern based on spatiotemporal trajectory information

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 29

Related Articles 6

Recommended Articles

Metrics

Comments