Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

Distance-Aware Vector-Field and Vector Screening Strategy for 6D Object Pose Estimation

  • Conference paper
  • First Online:

Abstract

6D object pose estimation calculates the rotation and translation matrices from the object coordinate system to the camera coordinate system and plays an important role in tasks such as robotic grasping. The voting-based 6D pose estimation method PVNet votes on a set of hypotheses to determine one as the estimation for real keypoint, and uses Perspective-n-Point (PnP) algorithm to calculate 6D pose based on the estimated keypoints. For improving the accuracy of estimated keypoints, the accuracy of hypotheses should be improved firstly. Since each hypothesis is an intersection computed with extended lines of two predicted unit vectors, three factors should be considered for improving its accuracy. The deviation of angle between predicted vector and real vector should be as small as possible. The angular deviation for predicted vectors of pixels farther away from keypoints should be smaller than that of those nearer. Any two approximately parallel or coincident predicted vectors should be prohibited to compute intersection. In light of the three points, this paper predicts vector-field instead of unit vector-field to take into account the distance from pixel to real keypoint, and proposes a distance-aware vector-field prediction loss which requires that the farther pixels from keypoints, the smaller the angular deviation for predicted vectors, and suggests a strategy for preventing approximately parallel or coincident predicted vectors from computing hypothesis. Experiments on LINEMOD and OCC-LINEMOD datasets show that our method achieves 5.9% and 8.4% improvement for the average accuracy of pose estimation in terms of ADD(-S) respectively compared with PVNet.

This research was supported by The National Key R & D Program of China (No.2021ZD0111902), NSFC(U21B2038, 61876012), Foundation for China university Industry-university Research Innovation (No.2021JQR023).

This is a preview of subscription content,log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 9151
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 11439
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Similar content being viewed by others

References

  1. Bay, H., Tuytelaars, T., Van, Gool. L.: Surf: Speeded up robust features. In: Proceedings of the European Conference on Computer Vision, pp. 404–417 (2006)

    Google Scholar 

  2. Lowe, D. G.: Object recognition from local scale-invariant features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1150–1157 (1999)

    Google Scholar 

  3. Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2564–2571 (2011)

    Google Scholar 

  4. Rosten, E., Drummond, T.: Fusing points and lines for high performance tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1508–1515 (2005)

    Google Scholar 

  5. Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: Pvnet: pixel-wise voting network for 6dof pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4561–4570 (2019)

    Google Scholar 

  6. Yu, X., Zhuang, Z., Koniusz, P., Li, H.: 6dof object pose estimation via differentiable proxy voting regularizer. In: British Machine Vision Conference, pp. 1–12 (2020)

    Google Scholar 

  7. Song, C., Song, J., Huang, Q.: HybridPose: 6d object pose estimation under hybrid representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 431–440 (2020)

    Google Scholar 

  8. Liu, X., Iwase, S., Kitani, K. M.: KdfNet: Learning keypoint distance field for 6d object pose estimation. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4631–4638 (2021)

    Google Scholar 

  9. Xiong, F., Liu, C., Chen, Q.: Region pixel voting network (RPVNet) for 6d pose estimation from monocular image. Appl. Sci.11(2), 743–757 (2021)

    Article  Google Scholar 

  10. Rad, M., Lepetit, V.: Bb8: a scalable, accurate, robust to partial occlusion method for predicting the 3d poses of challenging objects without using depth. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3828–3836 (2017)

    Google Scholar 

  11. Tekin, B., Sinha, S. N., Fua, P.: Real-time seamless single shot 6d object pose prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 292–301 (2018)

    Google Scholar 

  12. Zhao, W., Zhang, S., Guan, Z., Zhao, W., Peng, J., Fan, J.: Learning deep network for detecting 3d object keypoints and 6d poses. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 14134–14142 (2020)

    Google Scholar 

  13. Pavlakos, G., Zhou, X., Chan, A., Derpanis, K. G., Daniilidis, K.: 6-dof object pose from semantic keypoints. In: 2017 IEEE International Conference on Robotics and Automation, pp. 2011–2018 (2017)

    Google Scholar 

  14. Hu, Y., Hugonot, J., Fua, P., Salzmann, M.: Segmentation-driven 6d object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3385–3394 (2019)

    Google Scholar 

  15. Oberweger, M., Rad, M., Lepetit, V.: Making deep heatmaps robust to partial occlusions for 3d object pose estimation. In: Proceedings of the European Conference on Computer Vision, pp. 119–134 (2018)

    Google Scholar 

  16. Di, Y., Manhardt, F., Wang, G., Ji, X., Navab, N., Tombari, F.: So-pose: exploiting self-occlusion for direct 6d pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 12396–12405 (2021)

    Google Scholar 

  17. Hodan, T., Barath, D., Matas, J.: Epos: Estimating 6d pose of objects with symmetries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11703–11712 (2020)

    Google Scholar 

  18. Li, Z., Wang, G., Ji, X.: Cdpn: Coordinates-based disentangled pose network for real-time RGB-based 6-DOF object pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7678–7687 (2019)

    Google Scholar 

  19. Wang, G., Manhardt, F., Tombari, F., Ji, X.: GDR-net: geometry-guided direct regression network for monocular 6d object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16611–16621 (2021)

    Google Scholar 

  20. Zakharov, S., Shugurov, I., Ilic, S.: Dpod: 6d pose object detector and refiner. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1941–1950 (2019)

    Google Scholar 

  21. Chen, B., Parra, A., Cao, J., Li, N., Chin, T. J.: End-to-end learnable geometric vision by backpropagating pnp optimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8100–8109 (2020)

    Google Scholar 

  22. Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)

    Google Scholar 

  23. Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: PoseCNN: a convolutional neural network for 6d object pose estimation in cluttered scenes. In: Robotics: Science and Systems Conference, pp. 19–32 (2018)

    Google Scholar 

  24. Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Scene coordinate regression forests for camera relocalization in RGB-D images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2930–2937 (2013)

    Google Scholar 

  25. Nigam, A., Penate-Sanchez, A., Agapito, L.: Detect globally, label locally: Learning accurate 6-DOF object pose estimation by joint segmentation and coordinate regression. IEEE Robot. Autom. Lett.3(4), 3960–3967 (2018)

    Article  Google Scholar 

  26. Lepetit, V., Moreno-Noguer, F., Fua, P.: EPnP: an accurate O(n) solution to the PnP problem. Int. J. Comput. Vision81(2), 155–166 (2009)

    Article  Google Scholar 

  27. Brachmann, E., Krull, A., Michel, F., Gumhold, S., Shotton, J., Rother, C.: Learning 6d object pose estimation using 3d object coordinates. In: Proceedings of the European Conference on Computer Vision, pp. 536–551 (2014)

    Google Scholar 

  28. Michel, F., et al.: Global hypothesis generation for 6D object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 462–471 (2017)

    Google Scholar 

  29. Brachmann, E., Michel, F., Krull, A., Yang, M. Y., Gumhold, S.: Uncertainty-driven 6d pose estimation of objects and scenes from a single RGB image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3364–3372 (2016)

    Google Scholar 

  30. Hinterstoisser, S., et al.: Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: Asian Conference on Computer Vision, pp. 548–562 (2012)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China

    Lichun Wang, Chao Yang, Jianjia Xin & Baocai Yin

  2. Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, Beijing, 100124, China

    Lichun Wang, Chao Yang, Jianjia Xin & Baocai Yin

Authors
  1. Lichun Wang

    You can also search for this author inPubMed Google Scholar

  2. Chao Yang

    You can also search for this author inPubMed Google Scholar

  3. Jianjia Xin

    You can also search for this author inPubMed Google Scholar

  4. Baocai Yin

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toLichun Wang.

Editor information

Editors and Affiliations

  1. Dalian University of Technology, Dalian, China

    Huchuan Lu

  2. University of Sydney, Sydney, NSW, Australia

    Wanli Ouyang

  3. Shenzhen University, Shenzhen, China

    Hui Huang

  4. Tsinghua University, Beijing, China

    Jiwen Lu

  5. Dalian University of Technology, Dalian, China

    Risheng Liu

  6. Institute of Automation, CAS, Beijing, China

    Jing Dong

  7. University of Technology Sydney, Sydney, NSW, Australia

    Min Xu

Rights and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wang, L., Yang, C., Xin, J., Yin, B. (2023). Distance-Aware Vector-Field and Vector Screening Strategy for 6D Object Pose Estimation. In: Lu, H.,et al. Image and Graphics. ICIG 2023. Lecture Notes in Computer Science, vol 14356. Springer, Cham. https://doi.org/10.1007/978-3-031-46308-2_31

Download citation

Publish with us

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 9151
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 11439
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

[8]ページ先頭
©2009-2025 Movatter.jp