Temporal Semantic Motion Segmentation Using Spatio Temporal Optimization

  • Nazrul HaqueEmail author
  • N. Dinesh Reddy
  • Madhava Krishna
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10746)


Segmenting moving objects in a video sequence has been a challenging problem and critical to outdoor robotic navigation. While recent literature has laid focus on regularizing object labels over a sequence of frames, exploiting the spatio-temporal features for motion segmentation has been scarce. Particularly in real world dynamic scenes, existing approaches fail to exploit temporal consistency in segmenting moving objects with large camera motion.

In this paper, we present an approach for exploiting semantic information and temporal constraints in a joint framework for motion segmentation in a video. We propose a formulation for inferring per-frame joint semantic and motion labels using semantic potentials from dilated CNN framework and motion potentials from depth and geometric constraints. We integrate the potentials obtained into a 3D (space-time) fully connected CRF framework with overlapping/connected blocks. We solve for a feature space embedding in the spatio-temporal space by enforcing temporal constraints using optical flow and long term tracks as a least-squares problem. We evaluate our approach on outdoor driving benchmarks - KITTI and Cityscapes dataset.


  1. 1.
    Badrinarayanan, V., Handa, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv preprint arXiv:1505.07293 (2015)
  2. 2.
    Chen, T., Lu, S.: Object-level motion detection from moving cameras. IEEE Trans. Circ. Syst. Video Technol. 27, 2333–2343 (2016)CrossRefGoogle Scholar
  3. 3.
    Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)Google Scholar
  4. 4.
    Dollár, P., Zitnick, C.L.: Fast edge detection using structured forests. PAMI 37, 1558–1570 (2015)CrossRefGoogle Scholar
  5. 5.
    Fragkiadaki, K., Arbeláez, P., Felsen, P., Malik, J.: Learning to segment moving objects in videos. In: CVPR. IEEE (2015)Google Scholar
  6. 6.
    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: CVPR (2012)Google Scholar
  7. 7.
    Geiger, A., Ziegler, J., Stiller, C.: Stereoscan: Dense 3D reconstruction in real-time. In: Intelligent Vehicles Symposium (IV) (2011)Google Scholar
  8. 8.
    Haque, N., Reddy, D., Krishna, M.: Joint semantic and motion segmentation for dynamic scenes using deep convolutional networks. In: VISAPP (2017)Google Scholar
  9. 9.
    Hirschmuller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. PAMI 30, 328–341 (2008)CrossRefGoogle Scholar
  10. 10.
    Huang, S.J., Yu, Y., Zhou, Z.H.: Multi-label hypothesis reuse. In: KDD. ACM (2012)Google Scholar
  11. 11.
    Jain, S., Madhav Govindu, V.: Efficient higher-order clustering on the grassmann manifold. In: ICCV, pp. 3511–3518 (2013)Google Scholar
  12. 12.
    Koltun, V.: Efficient inference in fully connected CRFS with Gaussian edge potentials. In: NIPS (2011)Google Scholar
  13. 13.
    Kundu, A., Krishna, K., Sivaswamy, J.: Moving object detection by multi-view geometric techniques from a single camera mounted robot. In: IROS (2009)Google Scholar
  14. 14.
    Kundu, A., Vineet, V., Koltun, V.: Feature space optimization for semantic video segmentation. In: CVPR (2016)Google Scholar
  15. 15.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: ICCV, pp. 3431–3440 (2015)Google Scholar
  16. 16.
    Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: ICCV, pp. 1520–1528 (2015)Google Scholar
  17. 17.
    Reddy, N.D., Singhal, P., Chari, V., Krishna, K.M.: Dynamic body VSLAM with semantic constraints. In: IROS (2015)Google Scholar
  18. 18.
    Reddy, N.D., Singhal, P., Krishna, K.M.: Semantic motion segmentation using dense CRF formulation. In: ICVGIP (2014)Google Scholar
  19. 19.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR (2016)Google Scholar
  20. 20.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)Google Scholar
  21. 21.
    Ros, G., Ramos, S., Granados, M., Bakhtiary, A., Vazquez, D., Lopez, A.: Vision-based offline-online perception paradigm for autonomous driving. In: WACV (2015)Google Scholar
  22. 22.
    Shotton, J., Johnson, M., Cipolla, R.: Semantic texton forests for image categorization and segmentation. In: CVPR. IEEE (2008)Google Scholar
  23. 23.
    Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568–576 (2014)Google Scholar
  24. 24.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)
  25. 25.
    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. LNCS, vol. 6311, pp. 438–451. Springer, Heidelberg (2010). CrossRefGoogle Scholar
  26. 26.
    Tourani, S., Krishna, K.M.: Using in-frame shear constraints for monocular motion segmentation of rigid bodies. JIRS 82(2), 237–255 (2016)Google Scholar
  27. 27.
    Vertens, J., Valada, A., Burgard, W.: SMSnet: semantic motion segmentation using deep convolutional neural networks. In: IROS (2017)Google Scholar
  28. 28.
    Vidal, R., Sastry, S.: Optimal segmentation of dynamic scenes from two perspective views. In: CVPR, vol. 2 (2003)Google Scholar
  29. 29.
    Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: Deepflow: large displacement optical flow with deep matching. In: ICCV (2013)Google Scholar
  30. 30.
    Yi, S., Li, H., Wang, X.: Pedestrian behavior understanding and prediction with deep neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 263–279. Springer, Cham (2016). CrossRefGoogle Scholar
  31. 31.
    Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
  32. 32.
    Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.H.: Conditional random fields as recurrent neural networks. In: ICCV, pp. 1529–1537 (2015)Google Scholar
  33. 33.
    Zografos, V., Nordberg, K.: Fast and accurate motion segmentation using linear combination of views. In: BMVC (2011)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Nazrul Haque
    • 1
    Email author
  • N. Dinesh Reddy
    • 2
  • Madhava Krishna
    • 1
  1. 1.International Institute of Information TechnologyHyderabadIndia
  2. 2.Robotic InstituteCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations