Local Behavior Analysis for Trajectory Classification Using Graph Embedding

Understanding motion patterns is of great importance to analyze the behavior of objects in the vigilance area. Grouping the motion patterns into clusters in such a way that similar motion patterns lie in same cluster and the inter-cluster variance is maximized. Variation in the duration of trajectory patterns in terms of time or number of points in them (even in the trajectories from same cluster) make it more difficult to correctly classify in respective clusters as a bijective mapping is not possible in such cases. In this paper, we have formulated the trajectory classification problem into graph based similarity problem using Douglas-Peucker (DP) algorithm and complete bipartite graphs. Local behavior of objects has been analyzed using their motion segments and Dynamic Time Warping (DTW) has been used for finding similarity among motion trajectories. Class-wise global and local costs have been computed using DTW and their fusion has been done using Particle Swarm Optimization (PSO) to improve the classification rate. Experiments have been performed using two public trajectory datasets, namely T15 and LabOmni. The proposed method yields encouraging results and outperforms the state of the art techniques.

[1]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[2]  G. Salvi,et al.  An Automated Nighttime Vehicle Counting and Detection System for Traffic Surveillance , 2014, 2014 International Conference on Computational Science and Computational Intelligence.

[3]  Kaspar Riesen,et al.  A Survey on Applications of Bipartite Graph Edit Distance , 2017, GbRPR.

[4]  H. Fradi,et al.  Robust foreground segmentation using improved Gaussian Mixture Model and optical flow , 2012, 2012 International Conference on Informatics, Electronics & Vision (ICIEV).

[5]  Debi Prosad Dogra,et al.  An efficient approach for trajectory classification using FCM and SVM , 2017, 2017 IEEE Region 10 Symposium (TENSYMP).

[6]  David H. Douglas,et al.  ALGORITHMS FOR THE REDUCTION OF THE NUMBER OF POINTS REQUIRED TO REPRESENT A DIGITIZED LINE OR ITS CARICATURE , 1973 .

[7]  Zhongfei Zhang,et al.  An Incremental DPMM-Based Method for Trajectory Clustering, Modeling, and Retrieval , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Jing Wang,et al.  Integrated the Simplified Interpolation and Clonal Selection into the Particle Swarm Optimization for Optimization Problems , 2006, SEAL.

[9]  Takashi Fuse,et al.  Statistical Anomaly Detection in Human Dynamics Monitoring Using a Hierarchical Dirichlet Process Hidden Markov Model , 2017, IEEE Transactions on Intelligent Transportation Systems.

[10]  Nannan Li,et al.  Hierarchical activity discovery within spatio-temporal context for video anomaly detection , 2013, 2013 IEEE International Conference on Image Processing.

[11]  Siak Wang Khor,et al.  Path clustering using Dynamic Time Warping technique , 2012, 2012 8th International Conference on Computing Technology and Information Management (NCM and ICNIT).

[12]  Huiying Xu,et al.  Supervision on abnormal activities in vehicle inspection service by anomaly detection in bipartite graph , 2016, 2016 IEEE International Conference on Intelligent Transportation Engineering (ICITE).

[13]  Wolfram Burgard,et al.  A Tutorial on Graph-Based SLAM , 2010, IEEE Intelligent Transportation Systems Magazine.

[14]  Yunsick Sung,et al.  3D UAV Flying Path Optimization Method Based on the Douglas-Peucker Algorithm , 2017, MUE/FutureTech.

[15]  Diansheng Guo,et al.  A graph-based approach to vehicle trajectory analysis , 2010, J. Locat. Based Serv..

[16]  Carlos González,et al.  LIDAR based perception solution for autonomous vehicles , 2011, 2011 11th International Conference on Intelligent Systems Design and Applications.

[17]  Debi Prosad Dogra,et al.  Classification of Object Trajectories Represented by High-Level Features Using Unsupervised Learning , 2016, CVIP.

[18]  Bogdan Gabrys,et al.  Comparing and Combining Time Series Trajectories Using Dynamic Time Warping , 2016, KES.

[19]  Rongrong Ji,et al.  3D object retrieval with multi-feature collaboration and bipartite graph matching , 2016, Neurocomputing.

[20]  Hongyuan Zha,et al.  Unsupervised Trajectory Clustering via Adaptive Multi-kernel-Based Shrinkage , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[21]  Debi Prosad Dogra,et al.  Study of Text Segmentation and Recognition Using Leap Motion Sensor , 2017, IEEE Sensors Journal.

[22]  Kyuchang Kang,et al.  Hierarchically linked infinite hidden Markov model based trajectory analysis and semantic region retrieval in a trajectory dataset , 2017, Expert Syst. Appl..

[23]  Mohan M. Trivedi,et al.  Learning trajectory patterns by clustering: Experimental studies and comparative evaluation , 2009, CVPR.