Advertisement

International Journal of Computer Vision

, Volume 112, Issue 2, pp 188–203 | Cite as

Towards Scene Understanding with Detailed 3D Object Representations

  • M. Zeeshan Zia
  • Michael Stark
  • Konrad Schindler
Article

Abstract

Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard much of the information about objects’ 3D shape and pose, and thus do not lend themselves well to higher-level reasoning. Here, we propose to base scene understanding on a high-resolution object representation. An object class—in our case cars—is modeled as a deformable 3D wireframe, which enables fine-grained modeling at the level of individual vertices and faces. We augment that model to explicitly include vertex-level occlusion, and embed all instances in a common coordinate frame, in order to infer and exploit object-object interactions. Specifically, from a single view we jointly estimate the shapes and poses of multiple objects in a common 3D frame. A ground plane in that frame is estimated by consensus among different objects, which significantly stabilizes monocular 3D pose estimation. The fine-grained model, in conjunction with the explicit 3D scene model, further allows one to infer part-level occlusions between the modeled objects, as well as occlusions by other, unmodeled scene elements. To demonstrate the benefits of such detailed object class models in the context of scene understanding we systematically evaluate our approach on the challenging KITTI street scene dataset. The experiments show that the model’s ability to utilize image evidence at the level of individual parts improves monocular 3D pose estimation w.r.t. both location and (continuous) viewpoint.

Keywords

Ground Plane Object Instance Scene Understanding Object Hypothesis Occlusion Pattern 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgments

This work has been supported by the Max Planck Center for Visual Computing & Communication.

References

  1. Bao, S. Y., & Savarese, S. (2011). Semantic structure from motion. In CVPR.Google Scholar
  2. Belongie, S., Malik, J., & Puzicha, J. (2000). Shape context: A new descriptor for shape matching and object recognition. In NIPS.Google Scholar
  3. Bourdev, L., & Malik, J. (2009). Poselets: Body part detectors trained using 3D human pose annotations. In ICCV.Google Scholar
  4. Brooks, R. A. (1981). Symbolic reasoning among 3-d models and 2-d images. Artificial Intelligence, 17, 285–348.CrossRefGoogle Scholar
  5. Choi, W., Chao, Y. -W., Pantofaru, C., & Savarese, S. (2013). Understanding indoor scenes using 3D geometric phrases. In CVPR.Google Scholar
  6. Cootes, T. F., Taylor, C. J., Cooper, D. H., & Graham, J. (1995). Active shape models, their training and application. Computer Vision and Image Understanding, 61(1), 38–59.CrossRefGoogle Scholar
  7. Dalal, N., Triggs, B. (2005). Histograms of oriented gradients for human detection. In CVPR.Google Scholar
  8. Del Pero, L., Bowdish, J., Kermgard, B., Hartley, E., & Barnard, K. (2013). Understanding Bayesian rooms using composite 3D object models. In CVPR.Google Scholar
  9. Enzweiler, M., Eigenstetter, A., Schiele, B., & Gavrila, D. M. (2010). Multi-Cue pedestrian classification with partial occlusion handling. In CVPR.Google Scholar
  10. Ess, A., Leibe, B., Schindler, K., & Gool, L. V. (2009). Robust multi-person tracking from a mobile platform. Pattern Analysis and Machine Intelligence, 31(10), 1831–1846.CrossRefGoogle Scholar
  11. Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 88(2), 303–338.CrossRefGoogle Scholar
  12. Felzenszwalb, P. F., Girshick, R., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part based models. Pattern Analysis and Machine Intelligence, 32(9), 1627–1645.CrossRefGoogle Scholar
  13. Fransens, R., Strecha, C., & Gool, L. V. (2006). A mean field EM-algorithm for coherent occlusion handling in MAP-estimation. In CVPR.Google Scholar
  14. Gao, T., Packer, B., & Koller, D. (2011). A segmentation-aware object detection model with occlusion handling. In CVPR.Google Scholar
  15. Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving?. The KITTI vision benchmark suite. In CVPR.Google Scholar
  16. Geiger, A., Wojek, C., & Urtasun, R. (2011). Joint 3D estimation of objects and scene layout. In NIPS.Google Scholar
  17. Girshick, R. B., Felzenszwalb, P. F., & McAllester, D. (2011). Object detection with grammar models. In NIPS.Google Scholar
  18. Gupta, A., Efros, A. A., & Hebert, M. (2010). Blocks world revisited: Image understanding using qualitative geometry and mechanics. In ECCV.Google Scholar
  19. Haag, M., & Nagel, H.-H. (1999). Combination of edge element and optical flow estimates for 3d-model-based vehicle tracking in traffic image sequences. International Journal of Computer Vision, 35(3), 295–319.CrossRefGoogle Scholar
  20. Hedau, V., Hoiem, D., & Forsyth, D. A. (2010). Thinking inside the box: Using appearance models and context based on room geometry. In ECCV.Google Scholar
  21. Hejrati, M., & Ramanan, D. (2012). Analyzing 3D objects in cluttered images. In NIPS.Google Scholar
  22. Hoiem, D., Efros, A., & Hebert, M. (2008). Putting objects in perspective. International Journal of Computer Vision, 80(1), 3–15.CrossRefGoogle Scholar
  23. Kanade, T. (1980). A theory of Origami world. Artificial Intelligence, 13, 279–311.CrossRefzbMATHMathSciNetGoogle Scholar
  24. Koller, D., Daniilidis, K., & Nagel, H. H. (1993). Model-based object tracking in monocular image sequences of road traffic scenes. International Journal of Computer Vision, 10(3), 257–281.CrossRefGoogle Scholar
  25. Kwak, S., Nam, W., Han, B., & Han, J. H. (2011). Learning occlusion with likelihoods for visual tracking. In ICCV.Google Scholar
  26. Leibe, B., Leonardis, A., & Schiele, B. (2006). An implicit shape model for combined object categorization and segmentation. In Toward category-level object recognition.Google Scholar
  27. Leordeanu, M., & Hebert, M. (2008). Smoothing-based optimization. In CVPR.Google Scholar
  28. Li, Y., Gu, L., & Kanade, T. (2011). Robustly aligning a shape model and its application to car alignment of unknown pose. Pattern Analysis and Machine Intelligence, 33(9), 1860–1876.CrossRefGoogle Scholar
  29. Liu, X., Zhao, Y., & Zhu, S. -C. (2014). Single-view 3D scene parsing by attributed grammar. In CVPR.Google Scholar
  30. Lowe, D. (1987). Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence, 31(3), 355–395.CrossRefGoogle Scholar
  31. Maji, S., & Malik, J. (2009). Object detection using a max-margin hough transform. In CVPR.Google Scholar
  32. Malik, J. (1987). Interpreting line drawings of curved objects. International Journal of Computer Vision, 1(1), 73–103.CrossRefMathSciNetGoogle Scholar
  33. Meger, D., Wojek, C., Schiele, B., & Little, J. J. (2011). Explicit occlusion reasoning for 3d object detection. In BMVC.Google Scholar
  34. Oramas, J., De Raedt, L., & Tuytelaars, T. (2013). Allocentric pose estimation. In ICCV.Google Scholar
  35. Pentland, A. (1986). Perceptual organization and representation of natural form. Artificial Intelligence, 28, 293–331.CrossRefMathSciNetGoogle Scholar
  36. Pepik, B., Stark, M., Gehler, P., & Schiele, B. (2013). Occlusion patterns for object class detection. In CVPR.Google Scholar
  37. Roberts, L. G. (1963) Machine perception of three-dimensional solids, Ph.D. thesis, MIT.Google Scholar
  38. Schönborn, S., Forster, A., Egger, B., & Vetter, T. (2013). A Monte Carlo strategy to integrate detection and model-based face analysis. In GCPR.Google Scholar
  39. Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor segmentation and support inference from RGBD images. In ECCV.Google Scholar
  40. Stark, M., Goesele, M., & Schiele, B. (2010). Back to the future: Learning shape models from 3D CAD data. In BMVC.Google Scholar
  41. Sullivan, G. D., Worrall, A. D., & Ferryman, J. M. (1995). Visual object recognition using deformable models of vehicles. In IEEE workshop on context-based vision.Google Scholar
  42. Tang, S., Andriluka, M., & Schiele, B. (2012). Detection and tracking of occluded oeople. In BMVC.Google Scholar
  43. Vedaldi, A., & Zisserman, A. (2009). Structured output regression for detection with partial truncation. In NIPS.Google Scholar
  44. Villamizar, M., Grabner, H., Andrade-Cetto, J., Sanfeliu, A., Gool, L. V., & Moreno-Noguer, F. (2011). Efficient 3D object detection using multiple pose-specific classifiers. In BMVC.Google Scholar
  45. Wang, H., Gould, S., & Koller, D. (2010). Discriminative learning with latent variables for cluttered indoor scene understanding. In ECCV.Google Scholar
  46. Wang, X., Han, T., & Yan, S. (2009). An HOG-LBP human detector with partial occlusion handling. In ICCV.Google Scholar
  47. Wojek, C., Walk, S., Roth, S., Schindler, K., & Schiele, B. (2013). Monocular visual scene understanding: Understanding multi-object traffic scenes. In PAMI.Google Scholar
  48. Xiang, Y., & Savarese, S. (2013). Object detection by 3D aspectlets and occlusion reasoning. In 3dRR.Google Scholar
  49. Xiang, Y., & Savarese, S. (2012). Estimating the aspect layout of object categories. In CVPR.Google Scholar
  50. Zhao, Y., & Zhu, S. -C. (2013). Scene parsing by integrating function, geometry and appearance models. In CVPR.Google Scholar
  51. Zia, M. Z., Klank, U., & Beetz, M. (2009). Acquisition of a dense 3D model database for robotic vision. In ICAR.Google Scholar
  52. Zia, M. Z., Stark, M., & Schindler, K. (2013). Explicit occlusion modeling for 3D object class representations. In CVPR.Google Scholar
  53. Zia, M. Z., Stark, M., & Schindler, K. (2014). Are cars just 3D boxes? Jointly estimating the 3D shape of multiple objects. In CVPR.Google Scholar
  54. Zia, M. Z., Stark, M., Schiele, B., & Schindler, K. (2013). Detailed 3d representations for object recognition and modeling. Pattern Analysis and Machine Intelligence, 35(11), 2608–2623.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • M. Zeeshan Zia
    • 1
    • 2
  • Michael Stark
    • 3
  • Konrad Schindler
    • 1
  1. 1.Swiss Federal Institute of Technology (ETH)ZurichSwitzerland
  2. 2.Imperial College LondonLondonUK
  3. 3.Max Planck Institute for InformaticsSaarbrückenGermany

Personalised recommendations