Support Vector Motion Clustering

  • Isah A. Lawal, Fabio Poiesi, Davide Anguita, and Andrea Cavallaro. Support Vector Motion Clustering. IEEE Transactions on Circuits and Systems for Video Technology, PP, 2016. doi:10.1109/TCSVT.2016.2580401
    [BibTeX] [Abstract]

    We present a closed-loop unsupervised clustering method for motion vectors extracted from highly dynamic video scenes. Motion vectors are assigned to non-convex homogeneous clusters characterizing direction, size and shape of regions with multiple independent activities. The proposed method is based on Support Vector Clustering (SVC). Cluster labels are propagated over time via incremental learning. The proposed method uses a kernel function that maps the input motion vectors into a high dimensional space to produce non-convex clusters. We improve the mapping effectiveness by quantifying feature similarities via a blend of position and orientation affinities. We use the Quasiconformal Kernel Transformation to boost the discrimination of outliers. The temporal propagation of the clusters? identities is achieved via incremental learning based on the concept of feature obsolescence to deal with appearing and disappearing features. Moreover, we design an on-line clustering performance prediction algorithm used as a feedback (closed-loop) that refines the cluster model at each frame in an unsupervised manner. We evaluate the proposed method on synthetic datasets and real-world crowded videos, and show that our solution outperforms state-of-the-art approaches.

    @article{2016-06-LAWAL,
    author = {Isah A. Lawal and Fabio Poiesi and Davide Anguita and Andrea Cavallaro},
    journal = {{IEEE Transactions on Circuits and Systems for Video Technology}},
    title = {{Support Vector Motion Clustering}},
    date = {2016-06-13},
    year = {2016},
    volume = {PP},
    issue = {99},
    doi = {10.1109/TCSVT.2016.2580401},
    abstract = {We present a closed-loop unsupervised clustering method for motion vectors extracted from highly dynamic video scenes. Motion vectors are assigned to non-convex homogeneous clusters characterizing direction, size and shape of regions with multiple independent activities. The proposed method is based on Support Vector Clustering (SVC). Cluster labels are propagated over time via incremental learning. The proposed method uses a kernel function that maps the input motion vectors into a high dimensional space to produce non-convex clusters. We improve the mapping effectiveness by quantifying feature similarities via a blend of position and orientation affinities. We use the Quasiconformal Kernel Transformation to boost the discrimination of outliers. The temporal propagation of the clusters? identities is achieved via incremental learning based on the concept of feature obsolescence to deal with appearing and disappearing features. Moreover, we design an on-line clustering performance prediction algorithm used as a feedback (closed-loop) that refines the cluster model at each frame in an unsupervised manner. We evaluate the proposed method on synthetic datasets and real-world crowded videos, and show that our solution outperforms state-of-the-art approaches.}
    }

This entry was posted in Dissemination. Bookmark the permalink.

Comments are closed.