Advertisement

SPOT: Selective Point Cloud Voting for Better Proposal in Point Cloud Object Detection

Conference paper
  • 575 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12356)

Abstract

The sparsity of point clouds limits deep learning models on capturing long-range dependencies, which makes features extracted by the models ambiguous. In point cloud object detection, ambiguous features make it hard for detectors to locate object centers (Fig. 1) and finally lead to bad detection results. In this work, we propose Selective Point clOud voTing (SPOT) module, a simple effective component that can be easily trained end-to-end in point cloud object detectors to solve this problem. Inspired by probabilistic Hough voting, SPOT incorporates an attention mechanism that helps detectors focus on less ambiguous features and preserves their diversity of mapping to multiple object centers. For evaluating our module, we implement SPOT on advanced baseline detectors and test on two benchmark datasets of clutter indoor scenes, ScanNet and SUN RGB-D. Baselines enhanced by our module can stably improve results in agreement by a large margin and achieve new state-or-the-art detection, especially under more strict evaluation metric that adopts larger IoU threshold, implying our module is the key leading to high-quality object detection in point clouds.

Notes

Acknowledgment:

This work was partially funded by NSF awards IIS-1637941, IIS-1924937, and NVIDIA GPU donations.

References

  1. 1.
    Attneave, F.: Information aspects of visual perception. Psychol. Rev. 61, 183–193 (1954)CrossRefGoogle Scholar
  2. 2.
    Ballard, D.H.: Generalizing the Hough transform to detect arbitrary shapes. Pattern Recogn. 13(2), 111–122 (1981)CrossRefGoogle Scholar
  3. 3.
    Barlow, H.: Cerebral cortex as a model builder. In: Models of the Visual Cortex, pp. 37–46 (1985)Google Scholar
  4. 4.
    Binford, T.: Inferring surfaces from images. Artif. Intell. 17, 205–244 (1981)CrossRefGoogle Scholar
  5. 5.
    Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond euclidean data. IEEE Signal Process. Mag. 34(4), 18–42 (2017)CrossRefGoogle Scholar
  6. 6.
    Chen, Y., Liu, S., Shen, X., Jia, J.: Fast point R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 9775–9784 (2019)Google Scholar
  7. 7.
    Corbière, C., Thome, N., Bar-Hen, A., Cord, M., Pérez, P.: Addressing failure prediction by learning model confidence. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 2902–2913 (2019)Google Scholar
  8. 8.
    Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5828–5839 (2017)Google Scholar
  9. 9.
    Engelcke, M., Rao, D., Wang, D.Z., Tong, C.H., Posner, I.: Vote3Deep: fast object detection in 3D point clouds using efficient convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 1355–1361 (2017)Google Scholar
  10. 10.
    Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning (ICML), pp. 1050–1059 (2016)Google Scholar
  11. 11.
    Geifman, Y., El-Yaniv, R.: Selective classification for deep neural networks. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 4878–4887 (2017)Google Scholar
  12. 12.
    Geifman, Y., El-Yaniv, R.: SelectiveNet: a deep neural network with an integrated reject option. In: International Conference on Machine Learning (ICML), pp. 2151–2159 (2019)Google Scholar
  13. 13.
    Graham, B., Engelcke, M., Van Der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9224–9232 (2018)Google Scholar
  14. 14.
    Harris, C.G., et al.: A combined corner and edge detector. In: Alvey Vision Conference, vol. 15, pp. 10–5244 (1988)Google Scholar
  15. 15.
    Hou, J., Dai, A., Nießner, M.: 3D-SIS: 3D semantic instance segmentation of RGB-D scans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4421–4430 (2019)Google Scholar
  16. 16.
    Hough, P.V.: Machine analysis of bubble chamber pictures. In: Proceedings of the International Conference on High Energy Accelerators and Instrumentation, pp. 554–556 (1959)Google Scholar
  17. 17.
    Huang, Q., Wang, W., Neumann, U.: Recurrent slice networks for 3D segmentation of point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2626–2635 (2018)Google Scholar
  18. 18.
    Klokov, R., Lempitsky, V.: Escape from cells: deep Kd-networks for the recognition of 3D point cloud models. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 863–872 (2017)Google Scholar
  19. 19.
    Knopp, J., Prasad, M., Willems, G., Timofte, R., Van Gool, L.: Hough transform and 3D SURF for robust three dimensional classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 589–602. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15567-3_43CrossRefGoogle Scholar
  20. 20.
    Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: PointPillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12697–12705 (2019)Google Scholar
  21. 21.
    Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. Int. J. Comput. Vis. (IJCV) 77(1–3), 259–289 (2008)CrossRefGoogle Scholar
  22. 22.
    Liu, Y., Fan, B., Xiang, S., Pan, C.: Relation-shape convolutional neural network for point cloud analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8895–8904 (2019)Google Scholar
  23. 23.
    Lowe, D.: Three-dimensional object recognition from single two-dimensional images. Artif. Intell. 31, 355–395 (1987)CrossRefGoogle Scholar
  24. 24.
    Maji, S., Malik, J.: Object detection using a max-margin Hough transform. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1038–1045 (2009)Google Scholar
  25. 25.
    Maturana, D., Scherer, S.: VoxNet: a 3D convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922–928 (2015)Google Scholar
  26. 26.
    Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep Hough voting for 3D object detection in point clouds. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 9277–9286 (2019)Google Scholar
  27. 27.
    Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 652–660 (2017)Google Scholar
  28. 28.
    Qi, C.R., Su, H., Nießner, M., Dai, A., Yan, M., Guibas, L.J.: Volumetric and multi-view CNNs for object classification on 3D data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5648–5656 (2016)Google Scholar
  29. 29.
    Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 5099–5108 (2017)Google Scholar
  30. 30.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 91–99 (2015)Google Scholar
  31. 31.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. Int. J. Comput. Vis. (IJCV) 37, 151–172 (2000)CrossRefGoogle Scholar
  32. 32.
    Shi, S., et al.: PV-RCNN: Point-Voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10529–10538 (2020)Google Scholar
  33. 33.
    Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–779 (2019)Google Scholar
  34. 34.
    Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2020)Google Scholar
  35. 35.
    Song, S., Lichtenberg, S.P., Xiao, J.: SUN RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 567–576 (2015)Google Scholar
  36. 36.
    Song, S., Xiao, J.: Deep sliding shapes for amodal 3D object detection in RGB-D images. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), pp. 808–816 (2016)Google Scholar
  37. 37.
    Su, H., et al.: SPLATNet: sparse lattice networks for point cloud processing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2530–2539 (2018)Google Scholar
  38. 38.
    Velizhev, A., Shapovalov, R., Schindler, K.: Implicit shape models for object detection in 3D point clouds. In: International Society of Photogrammetry and Remote Sensing Congress, vol. 2, p. 2 (2012)Google Scholar
  39. 39.
    Wang, D.Z., Posner, I.: Voting for voting in online point cloud object detection. In: Robotics: Science and Systems, vol. 1, pp. 10–15607 (2015)Google Scholar
  40. 40.
    Wang, P., Vasconcelos, N.: Towards realistic predictors. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 36–51 (2018)Google Scholar
  41. 41.
    Woodford, O.J., Pham, M.T., Maki, A., Perbet, F., Stenger, B.: Demisting the hough transform for 3D shape recognition and registration. Int. J. Comput. Vis. (IJCV) 106, 332–341 (2014)CrossRefGoogle Scholar
  42. 42.
    Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1912–1920 (2015)Google Scholar
  43. 43.
    Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)CrossRefGoogle Scholar
  44. 44.
    Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: STD: Sparse-to-dense 3D object detector for point cloud. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1951–1960 (2019)Google Scholar
  45. 45.
    Yi, L., Zhao, W., Wang, H., Sung, M., Guibas, L.J.: GSPN: Generative shape proposal network for 3D instance segmentation in point cloud. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3947–3956 (2019)Google Scholar
  46. 46.
    Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4490–4499 (2018)Google Scholar
  47. 47.
    Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection. arXiv preprint arXiv:1908.09492 (2019)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Electrical and Computer EngineeringUniversity of CaliforniaSan DiegoUSA

Personalised recommendations