access icon free Human motion capture data recovery using trajectory-based matrix completion

Matrix completion has previously been used as a method to recover missing data in a mocap sequence. Improvments to this scheme by structuring motion capture data into an alternative representation for matrix completion are proposed. This representation takes advantage of the properties of mocap data and matrix completion to improve the reliability of matrix completion. Experiments show that the proposed motion capture data recovery method performs significantly better for nearly all tested motion sequences and amounts of missing data.

Inspec keywords: image motion analysis; image sequences; matrix algebra; data structures

Other keywords: human motion capture data recovery; missing data recovery; trajectory-based matrix completion; mocap sequence; motion capture data structuring

Subjects: Computer vision and image processing techniques; Algebra; Algebra; Optical, image and video signal processing; File organisation

References

    1. 1)
      • 5. Candès, E., Recht, B.: ‘Exact matrix completion via convex optimization’, Found. Comput. Math., 2009, 9, (6), pp. 717772 (doi: 10.1007/s10208-009-9045-5).
    2. 2)
      • 7. Cai, J.-F., Candès, E., Shen, Z.: ‘A singular value thresholding algorithm for matrix completion’, SIAM J. Optim., 2010, 20, (4), pp. 19561982 (doi: 10.1137/080738970).
    3. 3)
      • 2. Xiao, J., Feng, Y., Hu, W.: ‘Predicting missing markers in human motion capture using l1-sparse representation’, Comput. Animat. Virtual Worlds, 2011, 22, (2–3), pp. 221228 (doi: 10.1002/cav.413).
    4. 4)
      • 4. Lai, R.Y.Q., Yuen, P.C., Lee, K.K.W.: ‘Motion capture data completion and denoising by singular value thresholding’, Eurograph. 2011-Short Papers, 2011, pp. 4548.
    5. 5)
      • 3. Lou, H., Chai, J.: ‘Example-based human motion denoising’, IEEE Trans. Vis. Comput. Graphics, 2010, 16, (5), pp. 870879 (doi: 10.1109/TVCG.2010.23).
    6. 6)
      • 6. Barbic, J., Safonova, A., Pan, J.-Y., Faloutsos, C., Hodgins, J., Pollard, N.: ‘Segmenting motion capture data into distinct behaviors’. Proc. Graphics Interface 2004, London, Ontario, Canada, May 2004, pp. 2436.
    7. 7)
      • 1. Yi, B.-K., Sidiropoulos, N.D., Johnson, T., Jagadish, H.V., Faloutsos, C., Biliris, A.: ‘Online data mining for co-evolving time sequences’. 16th Int. Conf. Data Engineering 2000, San Diego, CA, USA, February 2000, pp. 1322.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2013.0442
Loading

Related content

content/journals/10.1049/el.2013.0442
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Correspondence
This article has following corresponding article(s):
in brief