Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

CylinderTag: An Accurate and Flexible Marker for Cylinder-Shape Objects Pose Estimation Based on Projective Invariants (2310.13320v1)

Published 20 Oct 2023 in cs.CV, cs.GR, and cs.RO

Abstract: High-precision pose estimation based on visual markers has been a thriving research topic in the field of computer vision. However, the suitability of traditional flat markers on curved objects is limited due to the diverse shapes of curved surfaces, which hinders the development of high-precision pose estimation for curved objects. Therefore, this paper proposes a novel visual marker called CylinderTag, which is designed for developable curved surfaces such as cylindrical surfaces. CylinderTag is a cyclic marker that can be firmly attached to objects with a cylindrical shape. Leveraging the manifold assumption, the cross-ratio in projective invariance is utilized for encoding in the direction of zero curvature on the surface. Additionally, to facilitate the usage of CylinderTag, we propose a heuristic search-based marker generator and a high-performance recognizer as well. Moreover, an all-encompassing evaluation of CylinderTag properties is conducted by means of extensive experimentation, covering detection rate, detection speed, dictionary size, localization jitter, and pose estimation accuracy. CylinderTag showcases superior detection performance from varying view angles in comparison to traditional visual markers, accompanied by higher localization accuracy. Furthermore, CylinderTag boasts real-time detection capability and an extensive marker dictionary, offering enhanced versatility and practicality in a wide range of applications. Experimental results demonstrate that the CylinderTag is a highly promising visual marker for use on cylindrical-like surfaces, thus offering important guidance for future research on high-precision visual localization of cylinder-shaped objects. The code is available at: https://github.com/wsakobe/CylinderTag.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. H. Chen, L. Wei, H. Liu, B. Shi, G. Zhang, and H. Zha, “MOUNT: Learning 6DoF motion prediction based on uncertainty estimation for delayed AR rendering,” IEEE Trans. Vis. Comput. Graph., early access, 2022, doi: 10.1109/TVCG.2022.3228807.
  2. G. Du, K. Wang, S. Lian, and K. Zhao, “Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review,” Artif. Intell. Rev., vol. 54, no. 3, pp. 1677–1734, Aug. 2021.
  3. N. Lv, Z. Jiang, Y. Huang, X. Meng, G. Meenakshisundaram, and J. Peng, “Generic content-based retrieval of marker-based motion capture data,” IEEE Trans. Vis. Comput. Graph., vol. 24, no. 6, pp. 1969–1982, Jun. 2018.
  4. K. Maximilian, H. Acshi, and O. Edwin, “Flexible layouts for fiducial tags,” in Proc. IEEE/RSJ Int. Conf. Intell. Rob. Syst., Macau, China, Nov. 2019, pp. 1898–1903.
  5. J. Wang and E. Olson, “AprilTag 2: Efficient and robust fiducial detection,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., Daejeon, Korea, Oct. 2016, pp. 4193–4198.
  6. S. Garrido-Jurado, R. Mun~~𝑛\tilde{n}over~ start_ARG italic_n end_ARGoz-Salinas, F. J. Madrid-Cuevas, and M. J. Marín-Jiménez, “Automatic generation and detection of highly reliable fiducial markers under occlusion,” Pattern Recognit., vol. 47, no. 6, pp. 2280–2292, Jun. 2014.
  7. M. Fiala, “ARTag, a fiducial marker system using digital techniques,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., San Diego, USA, Jun. 2005, pp. 590–596.
  8. M. Fiala, “Designing highly reliable fiducial markers,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 7, pp. 1317–1324, Jul. 2010.
  9. J. DeGol, T. Bretl, and D. Hoiem, “ChromaTag: A colored marker and fast detection algorithm,” in Proc. IEEE Int. Conf. Comput. Vis., Venice, Italy, Oct. 2017, pp. 1472–1481.
  10. D. Wagner, “ARToolKitPlus for pose tracking on mobile devices,” in Proc. Comput. Vis. Winter Workshop, St. Lambrecht, Austria, Feb. 2007, pp. 139–146.
  11. H. Tanaka, Y. Sumi, and Y. Matsumoto, “A Visual Marker for Precise Pose Estimation based on Lenticular Lenses,” in Proc. IEEE Int. Conf. Robot. Automat., Saint Paul, USA, Jun. 2012, pp. 5222–5227.
  12. H. Tanaka, K. Ogata, and Y. Matsumoto, “Solving pose ambiguity of planar visual marker by wavelike two-tone patterns,” in Proc. IEEE/RSJ Int. Conf. Intell. Rob. Syst., Vancouver, Canada, Sep. 2017, pp. 568–573.
  13. K. Tateno, I. Kitahara, and Y. Ohta, “A Nested Marker for Augmented Reality,” in Proc. IEEE Virtual Reality Conf., Charlotte, USA, Apr. 2007, pp. 259–262.
  14. F. Schweiger, B. Zeisl, P. Georgel, G. Schroth, E. Steinbach, and N. Navab, “Maximum detector response markers for sift and surf,” in Proc. Vis. Model. Vis. Workshop, Braunschweig, Germany, Nov. 2009, pp. 145–154.
  15. A. Herout, I. Szentandrási, M. Zacharias, M. Dubská, and R. Kajan, “Five shades of grey for fast and reliable camera pose estimation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Portland, USA, Jun. 2013, pp. 1384–1390.
  16. S. Garrido-Jurado, R. Munoz-Salinas, F. J. Madrid-Cuevas, and R. Medina-Carnicer, “Generation of fiducial marker dictionaries using mixed integer linear programming,” Pattern Recognit., vol. 51, pp. 481–491, Mar. 2016.
  17. M. Zhu, B. He, J. Yu, F. Yuan, and J. Liu, “HydraMarker: Efficient, flexible, and multifold marker field generation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 5, pp. 5849–5861, May 2023.
  18. S. Wang, M. Zhu, Y. Hu, D. Li, F. Yuan, and J. Yu, “Accurate Detection and Localization of Curved Checkerboard-Like Marker Based on Quadratic Form,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–11, Aug. 2022.
  19. L. B. Gatrell, W. A. Hoff, and C. W. Sklair, “Robust image features: Concentric contrasting circles and their image extraction,” in Proc. Cooperative Intell. Robot. Space II, Boston, USA, Mar. 1992, pp. 235–245.
  20. A. Xu and G. Dudek, “Fourier tag: A smoothly degradable fiducial marker system with configurable payload capacity,” in Proc. Can. Conf. Comput. Robot Vis., St. John’s, Canada, May 2011, pp. 40–47.
  21. F. Bergamasco, A. Albarelli, L. Cosmo, E. Rodola, and A. Torsello, “An accurate and robust artificial marker based on cyclic codes,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 38, no. 12, pp. 2359–2373, Dec. 2016.
  22. L. Calvet, P. Gurdjos, and V. Charvillat, “Camera tracking using concentric circle markers: Paradigms and algorithms,” in Proc. IEEE Int. Conf. Image Process., Orlando, USA, Oct. 2012, pp. 1361–1364.
  23. L. Calvet, P. Gurdjos, C. Griwodz, and S. Gasparini, “Detection and accurate localization of circular fiducials under highly challenging conditions,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Las Vegas, USA, Jun. 2016, pp. 562–570.
  24. F. Bergamasco, A. Albarelli, and A. Torsello, “Pi-Tag: A fast image-space marker design based on projective invariants,” Mach. Vis. Appl., vol. 24, no. 6, pp. 1295–1310, Aug. 2013.
  25. T. Birdal, I. Dobryden, and S. Ilic,“X-Tag: A fiducial tag for flexible and accurate bundle adjustment,” in Proc. Int. Conf. 3D Vis., Stanford, USA, Oct. 2016, pp. 556–564.
  26. Y. Watanabe, T. Kato, and I. Masatoshi, “Extended dot cluster marker for high-speed 3d tracking in dynamic projection mapping,” in Proc. IEEE Int. Symp. Mixed Augmented Reality, Nantes, France, Oct. 2017, pp. 52–61.
  27. G. Narita, Y. Watanabe, and M. Ishikawa, “Dynamic projection mapping onto deforming non-rigid surface using deformable dot cluster marker,” IEEE Trans. Vis. Comput. Graph., vol. 23, no. 3, pp. 1235–1248, Mar. 2016.
  28. E. Costanza, “D-touch: A consumer-grade tangible interface module and musical applications,” in Proc. Conf. Hum.-Comput. Interact., Crete, Greece, Sep. 2003, pp. 175–178.
  29. M. Kaltenbrunner and R. Bencina, “reacTIVision: A computer-vision framework for table-based tangible interaction,” in Proc. Int. Conf. Tangible Embedded Interact., Baton Rouge, USA, Feb. 2007, pp. 69–74.
  30. C. N. Klokmose, J. B. Kristensen, R. Bagge, and K. Halskov, “BullsEye: High-precision fiducial tracking for table-based tangible interaction,” in Proc. ACM Int. Conf. Interact. Tabletops Surfaces, Dresden, Germany, Nov. 2014, pp. 269–278.
  31. G. Yu, Y. Hu, and J. Dai, “Topotag: A robust and scalable topological fiducial marker system,” IEEE Trans. Vis. Comput. Graph., vol. 27, no. 9, pp. 3769–3780, Sep. 2021.
  32. O. Grinchuk, V. Lebedev, and V. Lempitsky, “Learnable visual markers,” in Proc. Adv. Neural Inform. Process. Syst. Conf., Barcelona, Spain, Dec. 2016, pp. 4143–4151.
  33. J. B. Peace, E. Psota, Y. Liu, and L. C. Perez, “E2Etag: An end-to-end trainable method for generating and detecting fiducial markers,” in Proc. Brit. Mach. Vis. Conf., Manchester, UK, Sep. 2020, pp. 52–61.
  34. M. B. Yaldiz, A. Meuleman, H. Jang, H. Ha, and M. H. Kim, “Deepformabletag: End-to-end generation and recognition of deformable fiducial markers,” ACM Trans. Graph., vol. 40, no. 4, pp. 1–14, Aug. 2021.
  35. J. Pan, P. Zhang, J. Wang, M. Liu, and J. Yu, “Learning for depth control of a robotic penguin: A data-driven model predictive control approach,” IEEE Trans. Ind. Electron., early access, 2022, doi: 10.1109/TIE.2022.3225840.
  36. V. S. Tsonisp, K. V. Ch, and P. E. Trahaniaslj, “Landmark-based navigation using projective invariants,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., Victoria, Canada, Oct. 1998, pp. 342–347.
  37. R. V. Liere and J. D. Mulder, “Optical tracking using projective invariant marker pattern properties,” in Proc. IEEE Virtual Reality Conf., Los Angeles, USA, Apr. 2003, pp. 191–198.
  38. F. L. Coutinho and C. H. Morimoto, “Improving head movement tolerance of cross-ratio based eye trackers,” Int. J. Comput. Vis., vol. 101, no. 3, pp. 459–481, Jun. 2012.
  39. D. Q. Huynh, “The cross ratio: A revisit to its probability density function,” in Proc. Brit. Mach. Vis. Conf., Bristol, UK, Sep. 2000, pp. 1–10.
  40. T. Collins and A. Bartoli, “Infinitesimal plane-based pose estimation,” Int. J. Comput. Vis., vol. 109, no. 3, pp. 252–286, Sep. 2014.
  41. C. Grana, D. Borghesani, and R. Cucchiara, “Optimized block-based connected components labeling with decision trees,” IEEE Trans. Imag. Process., vol. 19, no. 6, pp. 1596–1609, Jun. 2010.
  42. Y. Hu, M. Zhu, S. Wang, D. Li, F. Yuan, and J. Yu, “A novel lightweight navigation system for oral and maxillofacial surgery using an external curved self-identifying checkerboard,” IEEE Trans. Automat. Sci. Eng., early access, 2023, doi:  10.1109/TASE.2023.3241325.
  43. A. Quattoni and A. Torralba, “Recognizing indoor scenes,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Miami, USA, Aug. 2009, pp. 413–420.
  44. L. Zhang, M. Ye, P. L. Chan, and G. Z. Yang, “Real-time surgical tool tracking and pose estimation using a hybrid cylindrical marker,” Int. J. Comput. Assisted Radiol. Surgery, vol. 12, no. 6, pp. 921–930, Jun. 2017.
  45. P. C. Wu, R. Wang, K. Kin, C. D. Twigg, S. Han, M. H. Yang, and S. Chien, “DodecaPen: Accurate 6DoF tracking of a passive stylus,” in Proc. Annu. ACM Symp. User Interface Softw. Technol., Quebec City, Canada, Oct. 2017, pp. 365–374.
  46. Z. Fan, G. Chen, J. Wang, and H. Liao, “Spatial position measurement system for surgical navigation using 3-D image marker-based tracking tools with compact volume,” IEEE Trans. Biomed. Eng., vol. 65, no. 2, pp. 378–389, Nov. 2017.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now