Trajectory classification is important for understanding object movements within the surveillance area. Raw trajectories are represented by object location in form of (x, y) coordinates. The length of trajectories varies in terms of number of points; thus, it is difficult to classify them into correct classes. The raw features extracted from trajectory do not yield satisfactory results in classification. Thus, robust features are needed that can efficiently represent trajectory sequences and help to improve the classification performance. In this paper, we present a new feature vector that is based on the concept of point-line duality (PLD) transformation, i.e., transformation of a trajectory point from its primal plane into a straight line in dual plane. Classification has been done using hidden Markov model (HMM) framework. We also propose a fusion approach combining classification results obtained from raw feature and PLD feature to improve the performance. Experiments have been carried out on raw trajectories with reduced lengths as well as adding Gaussian noise. Proposed approach has been tested on three publicly available datasets, namely T15, MIT, and CROSS. It has been found that the PLD feature outperforms existing features as well as raw feature when used in HHM-based classification. We have obtained encouraging results by feature combination at the decision level with 97, 96.75 and 99.80% accuracy, respectively, on T15, MIT, and CROSS datasets.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
Tax calculation will be finalised during checkout.
MIT dataset contains trajectories out of which many are noisy and/or very short in length. So only 400 trajectories were selected for experiments.
Appiah, K., Hunter, A., Lotfi, A., Waltham, C., Dickinson, P.: Human behavioural analysis with self-organizing map for ambient assisted living. In: IEEE International Conference on Fuzzy Systems, pp. 2430–2437 (2014)
Brun, L., Saggese, A., Vento, M.: Dynamic scene understanding for behavior analysis based on string kernels. IEEE Trans. CSVT 24(10), 1669–1681 (2014)
Cai, Y., Wang, H., Chen, X., Jiang, H.: Trajectory-based anomalous behaviour detection for intelligent traffic surveillance. IET Intell. Transp. Syst. 9(8), 810–816 (2015)
Dahmane, M. ,Meunier, J.:. Real-time video surveillance with self-organizing maps. In: Canadian Conference on Computer and Robot Vision, vol. 2, pp. 136–143 (2005)
David, D., Thomas, P.: Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica IJGIG 10, 112–122 (1973)
Dinh, T., Vo, N., Medioni, G.: Context tracker: exploring supporters and distracters in unconstrained environments. In: CVPR, pp. 1177–1184 (2011)
Dogra, D., Reddy, R., Subramanyam, K., Ahmed, A., Bhaskar, H.: Scene representation and anomalous activity detection using weighted region association graph. In: Proceedings of the of ICCVTA, pp. 104–112 (2015)
Domínguez, R., Onieva, E., Alonso, J., Villagra, J., González, C: Lidar based perception solution for autonomous vehicles. In: 2011 11th International Conference on Intelligent Systems Design and Applications (ISDA), pp. 790–795 (2011)
Fuse, T., Kamiya, K.: Statistical anomaly detection in human dynamics monitoring using a hierarchical dirichlet process hidden Markov model. IEEE Trans. Intell. Transp. Syst. PP(99), 1–10 (2017)
Hu, W., Li, X., Tian, G., Maybank, S., Zhang, Z.: An incremental DPMM-based method for trajectory clustering, modeling, and retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 35(5), 1051–1065. https://doi.org/10.1109/TPAMI.2012.188
Jan, T.: Neural network based threat assessment for automated visual surveillance. In: IEEE International Joint Conference on Neural Networks, vol. 2, pp. 1309–1312(2004)
Kihwan, K., Dongryeol, L., Irfan, E.: Gaussian process regression flow for analysis of motion trajectories. In: International Conference on Computer Vision, pp. 1164–1171 (2011)
Kim, E., Helal, S., Cook, D.: Human activity recognition and pattern discovery. Pervasive Comput. 9(1), 48–53 (2010)
Kumar, P., Gauba, H., Roy, P.P., Dogra, D.P.: A multimodal framework for sensor based sign language recognition. Neurocomputing 259, 21–38 (2017)
Kwon, Yongjin, Kang, Kyuchang, Jin, Junho, Moon, Jinyoung, Park, Jongyoul: Hierarchically linked infinite hidden Markov model based trajectory analysis and semantic region retrieval in a trajectory dataset. Expert Syst. Appl. 78, 386–395 (2017)
Lee, Anthony J.T., Chen, Yi-An, Ip, Weng-Chong: Mining frequent trajectory patterns in spatial-temporal databases. Inf. Sci. 179(13), 2218–2231 (2009)
Lee, J.G., Han, J., Li, X., Gonzalez, H.: Traclass: trajectory classification using hierarchical region-based and trajectory-based clustering. Proc VLDE 1(1), 1081–1094 (2008)
Mehta, P., Shah, H., Kori, V., Vikani, V., Shukla, S., Shenoy, M.: Survey of unsupervised machine learning algorithms on precision agricultural data. In ICIIECS, pp. 1–8 (2015)
Melo, J., Naftel, A., Bernardino, A., Santos-Victor, J.: Detection and classification of highway lanes using vehicle motion trajectories. IEEE Trans. ITS 7(2), 188–200 (2006)
Mozerov, M., Amato, A., Roca, F., Gonzlez, J.: Trajectory occlusion handling with multiple view distance minimization clustering. J Opt Eng 47, 2021–2029 (2008)
Nascimento, J., Figueiredo, M.A.T., Marques, J.S.: Trajectory classification using switched dynamical hidden markov models. IEEE Trans. Image Process. 19(5), 1338–1348 (2010)
O’Rourke, J.: Computational geometry in C, 2nd edn. Cambridge University Press, New York (1998)
Pan, X., Wang, H., He, Y., Xiong, W., Jian, T.: Online classification of frequent behaviours based on multidimensional trajectories. In: Sonar and Navigation, IET Radar (2017)
Pei, W., Dibeklioglu, H., Tax, D.M.J., van der Maaten, L.: Multivariate time-series classification using the hidden-unit logistic model. IEEE Trans. Neural Netw. Learn. Syst. PP(99), 1–12 (2017)
Pereira, E., Ciobanu, L., Cardoso, J.S.: Social signaling descriptor for group behavior analysis. In: Proceedings of Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), vol. 9117, pp. 13–22 (2015)
Piciarelli, C., Micheloni, C., Foresti, G.: Trajectory-based anomalous event detection. IEEE Trans. CSVT 18(11), 1544–1554 (2008)
Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)
Saini, R., Kumar, P., Dutta, S., Roy, P.P. Pal, U.: Local behavior analysis for trajectory classification using graph embedding. In: Asian Conference on Pattern Recognition (2017). (Accepted)
Saini, R., Roy, P.P., Dogra, D.P.: A segmental HMM based trajectory classification using genetic algorithm. Expert Syst. Appl. 93, 169–181 (2018)
Siang, K.L.Y., Khor, S.W.: Path clustering using dynamic time warping technique. ICCTIM 1, 449–452 (2012)
Sim, G., Chung, J., Sung, Y.: 3D UAV flying path optimization method based on the Douglas-Peucker algorithm. In: Park, J., Chen, S.C., Raymond Choo, K.K. (eds.) Advanced Multimedia and Ubiquitous Engineering. MUE 2017, FutureTech 2017. Lecture Notes in Electrical Engineering, vol. 448. Springer, Singapore (2017)
Suzuki, N., Hirasawa, K., Tanaka, K., Kobayashi, Y., Sato, Y., Fujino, Y.: Learning motion patterns and anomaly detection by human trajectory analysis. In: ICSMC, pp. 498–503 (2007)
Tang, K., Zhu, S., Xu, Y., Wang, F.: Modeling drivers’ dynamic decision-making behavior during the phase transition period: an analytical approach based on hidden markov model theory. IEEE Trans. Intell.Transp. Syst. 17(1), 206–214 (2016)
Tran, M.B., Trivedi, M.M.: Trajectory learning for activity understanding: unsupervised, multilevel, and long-term adaptive approach. IEEE Trans. PAMI 33(11), 2287–2301 (2011)
Xiaogang, W., Keng, T., Gee-Wah, N., Grimson, W.. Trajectory analysis and semantic region modeling using a nonparametric Bayesian model. In CVPR, pp. 1–8 (2008)
Xu, D., Wu, X., Song, D., Li, N., Chen, Y.L.: Hierarchical activity discovery within spatio-temporal context for video anomaly detection. In: ICIP, pp. 3597–3601 (2013)
Xu, H., Zhou, Y., Lin, W., Zha, H.: Unsupervised trajectory clustering via adaptive multi-kernel-based shrinkage. In: ICCV, pp. 4328–4336 (2015)
Zhong, J. Wentong, C., Luo, L., Yin, H.: Learning behavior patterns from video: A data-driven framework for agent-based crowd modeling. In Proceedings of the of ICAAMS, pp. 801–809 (2015)
About this article
Cite this article
Saini, R., Roy, P.P. & Dogra, D.P. A novel point-line duality feature for trajectory classification. Vis Comput 35, 415–427 (2019). https://doi.org/10.1007/s00371-018-1473-2
- Trajectory classification
- Hidden Markov model (HMM)
- Point-line duality (PLD)