Spatio-temporal Object Detection Proposals

  • Dan Oneata
  • Jerome Revaud
  • Jakob Verbeek
  • Cordelia Schmid
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8691)

Abstract

Spatio-temporal detection of actions and events in video is a challenging problem. Besides the difficulties related to recognition, a major challenge for detection in video is the size of the search space defined by spatio-temporal tubes formed by sequences of bounding boxes along the frames. Recently methods that generate unsupervised detection proposals have proven to be very effective for object detection in still images. These methods open the possibility to use strong but computationally expensive features since only a relatively small number of detection hypotheses need to be assessed. In this paper we make two contributions towards exploiting detection proposals for spatio-temporal detection problems. First, we extend a recent 2D object proposal method, to produce spatio-temporal proposals by a randomized supervoxel merging process. We introduce spatial, temporal, and spatio-temporal pairwise supervoxel features that are used to guide the merging process. Second, we propose a new efficient supervoxel method. We experimentally evaluate our detection proposals, in combination with our new supervoxel method as well as existing ones. This evaluation shows that our supervoxels lead to more accurate proposals when compared to using existing state-of-the-art supervoxel methods.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLICsuperpixels compared to state-of-the-art superpixel methods. PAMI 34(11), 2274–2282 (2012)CrossRefGoogle Scholar
  2. 2.
    Alexe, B., Deselares, T., Ferrari, V.: Measuring the objectness of image windows. PAMI 34(11), 2189–2202 (2012)CrossRefGoogle Scholar
  3. 3.
    Arbeláez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. PAMI 33(5), 898–916 (2011)CrossRefGoogle Scholar
  4. 4.
    Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 282–295. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Brox, T., Malik, J.: Large displacement optical flow: Descriptor matching in variational motion estimation. PAMI (2011)Google Scholar
  6. 6.
    Carreira, J., Caseiro, R., Batista, J., Sminchisescu, C.: Semantic segmentation with second-order pooling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 430–443. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  7. 7.
    Chen, A., Corso, J.: Propagating multi-class pixel labels throughout video frames. In: Proceedings of Western New York Image Processing Workshop (2010)Google Scholar
  8. 8.
    Cinbis, R., Verbeek, J., Schmid, C.: Segmentation driven object detection with Fisher vectors. In: ICCV (2013)Google Scholar
  9. 9.
    Corso, J., Sharon, E., Dube, S., El-Saden, S., Sinha, U., Yuille, A.: Efficient multilevel brain tumor segmentation with integrated Bayesian model classification. IEEE Trans. Med. Imaging 27(5), 629–640 (2008)CrossRefGoogle Scholar
  10. 10.
    Dollár, P., Zitnick, C.: Structured forests for fast edge detection. In: ICCV (2013)Google Scholar
  11. 11.
    Duchenne, O., Laptev, I., Sivic, J., Bach, F., Ponce, J.: Automatic annotation of human actions in video. In: ICCV (2009)Google Scholar
  12. 12.
    Endres, I., Hoiem, D.: Category independent object proposals. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 575–588. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  13. 13.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV 59(2), 167–181 (2004)CrossRefGoogle Scholar
  14. 14.
    Fowlkes, C., Belongie, S., Chung, F., Malik, J.: Spectral grouping using the nyström method. PAMI 26(2), 214–225 (2004)CrossRefGoogle Scholar
  15. 15.
    Gaidon, A., Harchaoui, Z., Schmid, C.: Actom sequence models for efficient action detection. In: CVPR (2011)Google Scholar
  16. 16.
    Galasso, F., Nagaraja, N., Cardenas, T., Brox, T., Schiele, B.: A unified video segmentation benchmark: Annotation, metrics and analysis. In: ICCV (2013)Google Scholar
  17. 17.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)Google Scholar
  18. 18.
    Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: CVPR (2010)Google Scholar
  19. 19.
    Jain, M., Jégou, H., Bouthemy, P.: Better exploiting motion for better action recognition. In: CVPR (2013)Google Scholar
  20. 20.
    Jain, M., van Gemert, J., Bouthemy, P., Jégou, H., Snoek, C.: Action localization with tubelets from motion. In: CVPR (2014)Google Scholar
  21. 21.
    Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: A large video database for human motion recognition. In: ICCV (2011)Google Scholar
  22. 22.
    Lampert, C., Blaschko, M., Hofmann, T.: Efficient subwindow search: a branch and bound framework for object localization. PAMI 31(12), 2129–2142 (2009)CrossRefGoogle Scholar
  23. 23.
    Li, Z., Gavves, E., van de Sande, K., Snoek, C., Smeulders, A.: Codemaps, segment classify and search objects locally. In: ICCV (2013)Google Scholar
  24. 24.
    Lu, J., Yang, H., Min, D., Do, M.: Patch match filter: Efficient edge-aware filtering meets randomized search for fast correspondence field estimation. In: CVPR (2013)Google Scholar
  25. 25.
    Ma, T., Latecki, L.: Maximum weight cliques with mutex constraints for video object segmentation. In: CVPR (2012)Google Scholar
  26. 26.
    Manén, S., Guillaumin, M., Gool, L.V.: Prime object proposals with randomized Prim’s algorithm. In: ICCV (2013)Google Scholar
  27. 27.
    Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009)Google Scholar
  28. 28.
    Oneata, D., Verbeek, J., Schmid, C.: Action and event recognition with Fisher vectors on a compact feature set. In: ICCV (2013)Google Scholar
  29. 29.
    Oneata, D., Verbeek, J., Schmid, C.: Efficient action localization with approximately normalized Fisher vectors. In: CVPR (2014)Google Scholar
  30. 30.
    Over, P., Awad, G., Michel, M., Fiscus, J., Sanders, G., Shaw, B., Kraaij, W., Smeaton, A., Quénot, G.: TRECVID 2012 – an overview of the goals, tasks, data, evaluation mechanisms and metrics. In: Proceedings of TRECVID (2012)Google Scholar
  31. 31.
    Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: ICCV (2013)Google Scholar
  32. 32.
    Paris, S., Durand, F.: A topological approach to hierarchical segmentation using mean shift. In: CVPR (2007)Google Scholar
  33. 33.
    Pele, O., Werman, M.: Fast and robust earth mover’s distances. In: ICCV (2009)Google Scholar
  34. 34.
    Prest, A., Leistner, C., Civera, J., Schmid, C., Ferrari, V.: Learning object class detectors from weakly annotated video. In: CVPR (2012)Google Scholar
  35. 35.
    Rodriguez, M., Ahmed, J., Shah, M.: Action MACH: a spatio-temporal maximum average correlation height filter for action recognition. In: CVPR (2008)Google Scholar
  36. 36.
    Sánchez, J., Perronnin, F., Mensink, T., Verbeek, J.: Image classification with the Fisher vector: Theory and practice. IJCV 105(3), 222–245 (2013)CrossRefMATHGoogle Scholar
  37. 37.
    Sundaram, N., Brox, T., Keutzer, K.: Dense point trajectories by gpu-accelerated large displacement optical flow. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 438–451. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  38. 38.
    Tran, D., Yuan, J.: Optimal spatio-temporal path discovery for video event detection. In: CVPR (2011)Google Scholar
  39. 39.
    Uijlings, J., van de Sande, K., Gevers, T., Smeulders, A.: Selective search for object recognition. IJCV 104(2), 154–171 (2013)CrossRefGoogle Scholar
  40. 40.
    van de Sande, K., Snoek, C., Smeulders, A.: Fisher and VLAD with FLAIR. In: CVPR (2014)Google Scholar
  41. 41.
    Van den Bergh, M., Roig, G., Boix, X., Manen, S., Gool, L.V.: Online video SEEDS for temporal window objectness. In: ICCV (2013)Google Scholar
  42. 42.
    Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)Google Scholar
  43. 43.
    Wang, X., Yang, M., Zhu, S., Lin, Y.: Regionlets for generic object detection. In: ICCV (2013)Google Scholar
  44. 44.
    Weber, O., Devir, Y., Bronstein, A., Bronstein, M., Kimmel, R.: Parallel algorithms for approximation of distance maps on parametric surfaces. ACM Trans. Graph. (2008)Google Scholar
  45. 45.
    Xu, C., Corso, J.: Evaluation of super-voxel methods for early video processing. In: CVPR (2012)Google Scholar
  46. 46.
    Xu, C., Whitt, S., Corso, J.: Flattening supervoxel hierarchies by the uniform entropy slice. In: ICCV (2013)Google Scholar
  47. 47.
    Xu, C., Xiong, C., Corso, J.J.: Streaming hierarchical video segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 626–639. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  48. 48.
    Yuan, J., Liu, Z., Wu, Y.: Discriminative subvolume search for efficient action detection. In: CVPR (2009)Google Scholar
  49. 49.
    Zhang, D., Javed, O., Shah, M.: Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. In: CVPR (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Dan Oneata
    • 1
  • Jerome Revaud
    • 1
  • Jakob Verbeek
    • 1
  • Cordelia Schmid
    • 1
  1. 1.InriaFrance

Personalised recommendations