Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 3, pp 3279–3286 | Cite as

Investigating image stitching for action recognition

  • Yufeng Li
  • Ping’an Li
  • Daozhong Lei
  • Yingchun Shi
  • Lixin Tan
Article
  • 169 Downloads

Abstract

Action recognition is usually a central problem for many practical applications, such as video annotations, video surveillance and human computer interaction. Most action recognition approaches are based on localized spatio-temporal features that can vary significantly when the viewpoint changes. However, their performance rapidly drops when the viewpoints of the training and testing data are different. In this paper, we propose a transfer learning framework for view-invariant action recognition by the way of sharing image stitching feature among different views. Experimental results on multi-view action recognition IXMAS dataset demonstrate that our method produces remarkably good results and outperforms baseline methods.

Keywords

Image stitching Transfer learning Action recognition 

Notes

Acknowledgements

This research is supported by the Scientific Research Project of Hunan Provincial Education Department, China. The research and application of UAV Aerial system based on image splicing using multiple cameras (Grant No. 16C1139).

References

  1. 1.
    Chang X, Ma Z, Lin M, Yang Y, Hauptmann A (2017) Feature interaction augmented sparse learning for fast kinect motion detection. In: IEEE transactions on image processingGoogle Scholar
  2. 2.
    Chang X, Ma Z, Yang Y, Zeng Z (2017) Hauptmann AG Bi-level semantic representation analysis for multimedia event detection. In: IEEE transactions on cyberneticsGoogle Scholar
  3. 3.
    Chang X, Nie F, Wang S, Yang Y, Zhou X, Zhang C (2017) Compound rank-k projections for bilinear analysis. In: IEEE transactions on neural networks and learning systemsGoogle Scholar
  4. 4.
    Farhadi A, Tabrizi MK (2008) Learning to recognize activities from the wrong view point. In: ECCVGoogle Scholar
  5. 5.
    Huang CH, Yeh YR, Wang YCF (2012) Recognizing actions across cameras by exploring the correlated subspace. In: ECCVGoogle Scholar
  6. 6.
    Li B, Camps OI, Sznaier M (2012) Cross-view activity recognition using hankelets. In: CVPRGoogle Scholar
  7. 7.
    Li R, Zickler T (2012) Discriminative virtual views for cross-view action recognition. In: CVPRGoogle Scholar
  8. 8.
    Liu J, Shah M, Kuipers B, Savarese S (2011) Cross-view action recognition via view knowledge transfer. In: CVPRGoogle Scholar
  9. 9.
    Reddy K, Liu J, Shah M (2009) Incremental action recognition using feature tree. In: ICCVGoogle Scholar
  10. 10.
    Sugiyama M, Nakajima S, Kawanabe M (2008) Direct importance estimation with model selection and its application to covariate shift adaptation. In: NIPSGoogle Scholar
  11. 11.
    Tuzal O, Porikli F, Meer P (2008) Pedestrian detection via classification on riemannian manifolds. IEEE Trans Pattern Anal Mach Intell 30(10):1713–1727CrossRefGoogle Scholar
  12. 12.
    Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: CVPRGoogle Scholar
  13. 13.
    Weinland D, Boyer E, Ronfard R (2007) Action recognition from arbitrary views using 3d exemplars. In: ICCVGoogle Scholar
  14. 14.
    Weinland D, Ronfard R, Boyer E (2011) A survey of vision-based methods for action representation, segmentation and recognition. Comput Vis Image Underst 115:224–241CrossRefGoogle Scholar
  15. 15.
    Wu X, Jia Y (2012) View-invariant action recognition using latent kernelized structural SVM. In: ECCVGoogle Scholar
  16. 16.
    Yan Y, Ricci E, Subramanian R, Lanz O, Sebe N (2013) No matter where you are: flexible graph-guided multi-task learning for multi-view head pose classification under target motion. In: IEEE international conference on computer visionGoogle Scholar
  17. 17.
    Yan Y, Ricci E, Subramanian R, Liu G, Sebe N (2014) Multitask linear discriminant analysis for view invariant action recognition. In: IEEE transactions on image processingGoogle Scholar
  18. 18.
    Yan Y, Xu C, Cai D, Corso J (2017) Weakly supervised actor-action segmentation via robust multi-task ranking. In: IEEE conference on computer vision and pattern recognitionGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  • Yufeng Li
    • 1
  • Ping’an Li
    • 1
  • Daozhong Lei
    • 1
  • Yingchun Shi
    • 1
  • Lixin Tan
    • 1
  1. 1.School of Electronic EngineeringHunan College of InformationHunanChina

Personalised recommendations