Advertisement

Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling

  • Jonas Uhrig
  • Marius Cordts
  • Uwe Franke
  • Thomas Brox
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9796)

Abstract

Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel’s direction towards its corresponding instance center. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance segmentation on the street scene datasets KITTI and Cityscapes. Our approach outperforms existing works by a large margin and can additionally predict absolute distances of individual instances from a monocular image as well as a pixel-level semantic labeling.

Keywords

Output Channel Object Instance Semantic Class Semantic Label Depth Class 
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.

References

  1. 1.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. Trans. PAMI 33(5), 898–916 (2011)CrossRefGoogle Scholar
  2. 2.
    Arbelez, P., Pont-Tuset, J., Barron, J., Marques, F., Malik, J.: Multiscale combinatorial grouping. In: CVPR (2014)Google Scholar
  3. 3.
    Chen, L.C., Fidler, S., Urtasun, R.: Beat the MTurkers: automatic image labeling from weak 3d supervision. In: CVPR (2014)Google Scholar
  4. 4.
    Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: ICLR (2015)Google Scholar
  5. 5.
    Chen, Y.T., Liu, X., Yang, M.H.: Multi-instance object segmentation with occlusion handling. In: CVPR (2015)Google Scholar
  6. 6.
    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
  7. 7.
    Dai, J., He, K., Sun, J.: Convolutional feature masking for joint object and stuff segmentation. In: CVPR (2015)Google Scholar
  8. 8.
    Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: CVPR (2016)Google Scholar
  9. 9.
    Everingham, M., Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303–338 (2009)CrossRefGoogle Scholar
  10. 10.
    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)Google Scholar
  11. 11.
    Girshick, R.: Fast R-CNN. In: ICCV (2015)Google Scholar
  12. 12.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)Google Scholar
  13. 13.
    Hariharan, B., Arbelez, P., Girshick, R., Malik, J.: Hypercolumns for object segmentation and fine-grained localization. In: CVPR (2015)Google Scholar
  14. 14.
    Hariharan, B., Arbeláez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VII. LNCS, vol. 8695, pp. 297–312. Springer, Heidelberg (2014)Google Scholar
  15. 15.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  16. 16.
    Hosang, J., Benenson, R., Dollr, P., Schiele, B.: What makes for effective detection proposals? Trans. PAMI 38(4), 814–830 (2016)Google Scholar
  17. 17.
    Kirillov, A., Schlesinger, D., Forkel, W., Zelenin, A., Zheng, S., Torr, P.H.S., Rother, C.: Efficient likelihood learning of a generic CNN-CRF model for semantic segmentation. In: [cs.CV] (2015). arXiv:1511.05067v2
  18. 18.
    Kumar, M.P., Ton, P.H.S., Zisserman, A.: Obj Cut. In: CVPR (2005)Google Scholar
  19. 19.
    Liang, X., Wei, Y., Shen, X., Yang, J., Lin, L., Yan, S.: Proposal-free network for instance-level object segmentation. In: [cs.CV] (2015). arXiv:1509.02636v2
  20. 20.
    Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 740–755. Springer, Heidelberg (2014)Google Scholar
  21. 21.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)Google Scholar
  22. 22.
    Papandreou, G., Chen, L., Murphy, K., Yuille, A.L.: Weakly- and semi-supervised learning of a DCNN for semantic image segmentation. In: ICCV (2015)Google Scholar
  23. 23.
    Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR (2016)Google Scholar
  24. 24.
    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
  25. 25.
    Ren, S., He, K., Girshick, R.B., Zhang, X., Sun, J.: Object detection networks on convolutional feature maps. In: [cs.CV] (2015). arXiv:1504.06066v1
  26. 26.
    Romera-Paredes, B., Torr, P.H.S.: Recurrent instance segmentation. In: [cs.CV] (2015). arXiv:1511.08250v2
  27. 27.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  28. 28.
    Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Silberman, N., Sontag, D., Fergus, R.: Instance segmentation of indoor scenes using a coverage loss. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 616–631. Springer, Heidelberg (2014)Google Scholar
  30. 30.
    Tighe, J., Niethammer, M., Lazebnik, S.: Scene parsing with object instances and occlusion ordering. In: CVPR (2014)Google Scholar
  31. 31.
    Wang, P., Shen, X., Lin, Z., Cohen, S., Price, B., Yuille, A.: Towards unified depth and semantic prediction from a single image. In: CVPR (2015)Google Scholar
  32. 32.
    Yang, Y., Hallman, S., Ramanan, D., Fowlkes, C.: Layered object models for image segmentation. Trans. PAMI 34(9), 1731–1743 (2012)CrossRefGoogle Scholar
  33. 33.
    Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016)Google Scholar
  34. 34.
    Zhang, Z., Schwing, A.G., Fidler, S., Urtasun, R.: Monocular object instance segmentation and depth ordering with cnns. In: ICCV (2015)Google Scholar
  35. 35.
    Zhang, Z., Fidler, S., Urtasun, R.: Instance-level segmentation with deep densely connected MRFs. In: CVPR (2016)Google Scholar
  36. 36.
    Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.H.S.: Conditional random fields as recurrent neural networks. In: ICCV (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Jonas Uhrig
    • 1
    • 2
  • Marius Cordts
    • 1
    • 3
  • Uwe Franke
    • 1
  • Thomas Brox
    • 2
  1. 1.Daimler AG R&DStuttgartGermany
  2. 2.University of FreiburgFreiburg im BreisgauGermany
  3. 3.TU DarmstadtDarmstadtGermany

Personalised recommendations