Abstract
This paper proposes a novel technique for clustering and classification of object trajectory-based video motion clips using spatiotemporal function approximations. Assuming the clusters of trajectory points are distributed normally in the coefficient feature space, we propose a Mahalanobis classifier for the detection of anomalous trajectories. Motion trajectories are considered as time series and modelled using orthogonal basis function representations. We have compared three different function approximations – least squares polynomials, Chebyshev polynomials and Fourier series obtained by Discrete Fourier Transform (DFT). Trajectory clustering is then carried out in the chosen coefficient feature space to discover patterns of similar object motions. The coefficients of the basis functions are used as input feature vectors to a Self- Organising Map which can learn similarities between object trajectories in an unsupervised manner. Encoding trajectories in this way leads to efficiency gains over existing approaches that use discrete point-based flow vectors to represent the whole trajectory. Our proposed techniques are validated on three different datasets – Australian sign language, hand-labelled object trajectories from video surveillance footage and real-time tracking data obtained in the laboratory. Applications to event detection and motion data mining for multimedia video surveillance systems are envisaged.
Similar content being viewed by others
References
Aghbari Z., Kaneko K., Makinouchi A. (2003) Content-trajectory approach for searching video databases. IEEE Trans. Multimedia 5(4): 516–531
Alon J., Sclaroff S., Kollios G., Pavlovic V.: Discovering clusters in motion time-series data. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2004)
Bashir F., Khokhar A., Schonfeld D.: Segmented trajectory-based indexing and retrieval of video data. In: Proceedings of IEEE International Conference on Image Processing, Spain, pp. 623–626 (2003)
Bashir F., Khokhar A., Schonfeld D.: A hybrid system for affine-invariant trajectory retrieval. In: Proceedings of ACM SIGMM Multimedia Information Retrieval Workshop, pp. 235–242 (2004)
Bashir F., Khokhar A., Schonfeld D.: HMM-based motion recognition system using segmented PCA. In: Proceedings of IEEE International Conference on Image Processing (ICIP 2005), Genoa, Italy (2005)
Bashir F., Ashfaq A., Khokhar A., Schonfeld D. (2006) View-invariant motion trajectory-based activity classification and recognition. ACM Multimedia Syst. 12(1): 45–54
Buzan D., Sclaroff S., Kollios G.: Extraction and clustering of motion trajectories in video. In: Proceedings of International Conference on Pattern Recognition (2004)
CAVIAR: Context aware vision using image-based active recognition. [Online]. Available: [http://homepages.inf.ed.ac.uk/rbf/CAVIAR]
Chan K., Fu A.: Efficient time series matching by wavelets. In: Proceedings of International Conference on Data Engineering, Sydney, pp. 126–133 (1999)
Chang S.-F., Chen W., Meng H.-J., Sundaram H., Zhong D. (1998) A fully automated content-based video search engine supporting spatiotemporal queries. IEEE Trans. Circuits Syst. Video Technol. 8(5): 602–615
Chen L., Ozsu M.-T., Oria V.: Robust and fast similarity search for moving object databases. In: Proceedings of ACM SIGMOD, Maryland, pp. 491–502 (2005)
Cui Y., Ng R.: Indexing spatio-temporal trajectories with Chebyshev polynomials. In: Proceedings of ACM SIGMOD Conference, pp. 599–610 (2004)
Dagtas S., Ali-Khatib W., Ghafor A., Kashyap R.-L. (2000) Models for motion-based video indexing and retrieval. IEEE Trans. Image Proc. 9(1): 88–101
Faloutsas C. Ranganathan M., Manolopoulos Y.: Fast subsequence matching in time-series databases. In: Proceedings of ACM SIGMOD Conference, pp. 419–429 (1994)
Hsieh J.-W., Yu, S-L., Chen, Y-S.: Trajectory-based video retrieval by string matching. In: Proceedings of International Conference on Image Processing, pp. 2243–2246 (2004)
Hsu C.-T., Teng S.-J.: Motion trajectory based video indexing and retrieval. In: Proceedings of IEEE International Conference on Image Processing, pp. 605–608 (2002)
Hu W., Tan T., Wang L., Maybank S. (2004) A survey on visual surveillance of object motion and behaviors. IEEE Trans. Syst. Man Cybern. C 34(3): 334–352
Hu W., Xiao X., Xie D., Tan T., Maybank S. (2004) Traffic accident prediction using 3-D model-based vehicle tracking. IEEE Trans. Vehicular Tech. 53(3): 677–694
Hu W., Xie D., Tan T., Maybank S. (2004) Learning activity patterns using fuzzy self-organizing neural networks. IEEE Trans. Syst. Man Cybern. B, 34(3): 1618–1626
Ivo F., Sbalzarinii J.-T.: Machine learning for biological classification applications. In: Technical Report Center for Turbulence Research, Proceedings of the Summer Program (2002)
Jain A.-K., Dubes R.-C. (1998) Algorithms for Clustering Data. Prentice Hall, Englewood Cliffs
Jeannin S., Divakaran A. (2001) MPEG-7 visual motion descriptors. IEEE Trans. Circuits Syst. Video Technol. 11(6): 720–724
Jin Y., Mokhtarian F.: Efficient video retrieval by motion trajectory. In: Proceedings of British Machine Vision Conference (2004)
Johnson N., Hogg D. (1996) Learning the distribution of object trajectories for event recognition. Image Vis. Comput. 14(8): 609–615
Johnson R.-A., Wichern D.-W. (1998) Applied Multivariate Statistical Analysis, 4th edn. Prentice-Hall, New Jersey
KDD archive [Online]. Available: [http://kdd.ics.uci.edu/databases/auslan2/auslan.data.html]
Keogh E., Chakrabarti K., Pazzani M., Mehrota S.: Locally adaptive dimensionality reduction for indexing large time series databases. In: Proceedings of ACM SIGMOD Conference, pp. 151–162 (2001)
Keogh E., Kasetty S. (2003) On the need for time series data mining benchmarks: A survey and empirical demonstration. Data Mining and Knowledge Discovery. 7(4): 349–371
Khalid S., Naftel A.: Evaluation of matching metrics for trajectory-based indexing and retrieval of video clips. In: Proceedings of 7th IEEE Workshop on Applications of Computer Vision, Colorado, pp. 242–249 (2005)
Kohonen T. (1997) Self-Organizing Maps, 2nd edn. Springer, Berlin Heidelberg New York
Naftel A., Khalid S.: Video sequence indexing through recovery of object-based motion trajectories. In: Proceedings of Irish Machine Vision and Image Processing Conference (IMVIP′04), Dublin, Eire. pp 232–239 (2004)
Owens J., Hunter A.: Application of the self-organising map to trajectory classification. In: Proceedings of IEEE International Workshop on Visual Surveillance, pp. 77–83 (2000)
Rea N., Dahyot R., Kokaram A.: Semantic event detection in sports through motion understanding. In: Proceedings of Conference on Image and Video Retrieval, Dublin, Ireland (2004)
Shim C., Chang J.: Content-based retrieval using trajectories of moving objects in video databases. In: Proceedings of IEEE 7th International Conference on Database Systems for Advanced Applications, pp. 169–170 (2001)
Shim C., Chang J.: Trajectory-based video retrieval for multimedia information systems. In: Proceedings of ADVIS, pp. 372–382 (2004)
Vlachos M., Kollios G., Gunopulos D.: Discovering similar multidimensional trajectories. In: Proceedings of International Conference on Data Engineering, pp. 673, (2002)
Wang L., Hu W., Tan T. (2003) Recent developments in human motion analysis. Pattern Recogn. 36(3): 585–601
Yacoob Y., Black M.-J. (1999) Parameterized modeling and recognition of activities. Comput. Vis. Image Underst. 73(2): 232–247
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Naftel, A., Khalid, S. Classifying spatiotemporal object trajectories using unsupervised learning in the coefficient feature space. Multimedia Systems 12, 227–238 (2006). https://doi.org/10.1007/s00530-006-0058-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-006-0058-5