Vehicle trajectory prediction based on Hidden Markov Model = Vehicle trajectory prediction based on Hidden Markov Model

다국어 초록 (Multilingual Abstract)

In Intelligent Transportation Systems (ITS), logistics distribution and mobile e-commerce, the real-time, accurate and reliable vehicle trajectory prediction has significant application value. Vehicle trajectory prediction can not only provide accurate location-based services, but also can monitor and predict traffic situation in advance, and then further recommend the optimal route for users. In this paper, firstly, we mine the double layers of hidden states of vehicle historical trajectories, and then determine the parameters of HMM (hidden Markov model) by historical data. Secondly, we adopt Viterbi algorithm to seek the double layers hidden states sequences corresponding to the just driven trajectory. Finally, we propose a new algorithm (DHMTP) for vehicle trajectory prediction based on the hidden Markov model of double layers hidden states, and predict the nearest neighbor unit of location information of the next k stages. The experimental results demonstrate that the prediction accuracy of the proposed algorithm is increased by 18.3% compared with TPMO algorithm and increased by 23.1% compared with Naive algorithm in aspect of predicting the next k phases` trajectories, especially when traffic flow is greater, such as this time from weekday morning to evening. Moreover, the time performance of DHMTP algorithm is also clearly improved compared with TPMO algorithm.

참고문헌 (Reference)

1 J. C. Ying, "on Advances in Geographic Information Systems" ACM Press 34-43, 2011

2 이동욱, "aCN-RB-tree: Constrained Network-Based Index for Spatio-Temporal Aggregation of Moving Object Trajectory" 한국인터넷정보학회 3 (3): 527-547, 2009

3 A. Houenou, "Vehicle trajectory prediction based on motion model and maneuver recognition" 4363-4369, 2013

4 S. J. Qiao, "Uncertain trajectory prediction of moving objects based on CTBN" 41 (41): 759-763, 2012

5 Dung Phan, "Triangulation Based Skeletonization and Trajectory Recovery for Handwritten Character Patterns" 한국인터넷정보학회 9 (9): 358-377, 2015

6 P. Liu, "Trajectory prediction of a lane changing vehicle based on driver behavior estimation and classification" 942-947, 2014

7 S. J. Qiao, "Trajectory prediction algorithm based on Gaussian mixture model" 26 (26): 21-32, 2015

8 K. Hongfa, "Trajectory Prediction Algorithm of Moving Object Based on MGM(1, N)" 37 (37): 662-666, 2012

9 L. Wangao, "Prediction of trajectory based on modified Bayesian inference" 33 (33): 1960-1963, 2013

10 A. Asahara, "Pedestrian-movement prediction based on mixed Markov-chain model" 25-33, 2011

11 S. Gambs, "Next place prediction using mobility Markov chains" 1-6, 2012

12 N. Mamoulis, "Mining, indexing, and querying historical spatiotemporal data" ACM Press 236-245, 2004

13 M. Morzy, "Mining frequent trajectories of moving objects for location prediction" Springer-Verlag 667-680, 2007

14 N. S. Pai, "Implementation of a Tour Guide Robot System Using RFID Technology and Viterbi Algorithm-Based HMM for Speech Recognition" 22 (22): 12-25, 2014

15 Eddy, "Hidden Markov models" 6 (6): 361-365, 1996

16 Xiaoqing Yin, "Background Subtraction for Moving Cameras based on trajectory-controlled segmentation and Label Inference" 한국인터넷정보학회 9 (9): 4092-4107, 2015

17 I. Kaparias, "A reliability-based dynamic re-routing algorithm for in-vehicle navigation" 974-979, 2010

18 Xuezhi Wen, "A rapid learning algorithm for vehicle classification" 295 (295): 395-406, 2015

19 S. J. Qiao, "A Self-Adaptive Parameter Selection Trajectory Prediction Approach via Hidden Markov Models" 16 (16): 284-296, 2015

20 Ning Ye, "A Method of Vehicle Route Prediction Based on Social Network Analysis" 15 (15): 1-10, 2015

21 Ning Ye, "A Method for Driving Route Predictions Based on Hidden Markov Model" 15 : 1-12, 2015