[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Next Best View Planning in a Single Glance: An Approach to Improve Object Recognition

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

Many real-world mobile or robotic vision systems encounter the problem of occlusion or unfavorable viewpoint in performing their tasks. A remedy to this issue is active vision, i.e. physically moving the camera or employ another camera to provide other viewpoints that hopefully provide more information for the task at hand. In the case of object recognition, an active vision system can help by offering classification decisions from another viewpoint when the current recognition confidence is low. A natural question, however, would be which next viewpoint is more effective in improving the object recognition performance. To determine the next best view, previous approaches either need multiple captures of the same object in specified poses, training datasets of 3D objects, or construction of occupancy grids. These methods are consequently computation, data, or observation intensive. In this paper, we propose a next best view method for object recognition that does not need any information about objects in other viewpoints, their 3D shape, or multiple prior observations to function properly. The proposed approach analyzes the object’s appearance and foreshortening in the current view to rapidly decide where to look next. Test results show its efficacy in correctly selecting the viewpoints that improve the object recognition performance more.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Data Availability

Yes. Dataset available at https://github.com/pouryahoseini/Next-Best-View-Dataset.

Code Availability

Yes. Code available at https://github.com/pouryahoseini/Next-Best-View.

Notes

  1. Dataset available at https://github.com/pouryahoseini/Next-Best-View-Dataset.

References

  1. Bajcsy R, Aloimonos Y, Tsotsos JK. Revisiting active perception. Autonom Robots. 2018;42(2):177–96.

    Article  Google Scholar 

  2. Hoseini P, Blankenburg J, Nicolescu M, Nicolescu M, Feil-Seifer D. An active robotic vision system with a pair of moving and stationary cameras. In: International symposium on visual computing. Springer; 2019. p. 184–195.

  3. Hoseini P, Blankenburg J, Nicolescu M, Nicolescu M, Feil-Seifer D. Active eye-in-hand data management to improve the robotic object detection performance. Computers. 2019;8(4):71.

    Article  Google Scholar 

  4. Hoseini P, Paul S.K, Nicolescu M, Nicolescu M.N. A surface and appearance-based next best view system for active object recognition. In: VISIGRAPP (5: VISAPP). 2021. p. 841–851.

  5. Hoseini P, Paul SK, Nicolescu M, Nicolescu M. A one-shot next best view system for active object recognition. Appl Intell. 2021;1–20.

  6. Wu Z, Song S, Khosla A, Yu F, Zhang L, Tang X, Xiao J. 3d shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 1912–1920.

  7. Zeng R, Zhao W, Liu Y-J. Pc-nbv: a point cloud based deep network for efficient next best view planning. In: 2020 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE; 2020. p. 7050–7057

  8. Wei W, Yu H, Zhang H, Xu W, Wu Y. Metaview: few-shot active object recognition. 2021. arXiv preprint arXiv:2103.04242.

  9. Barzilay O, Zelnik-Manor L, Gutfreund Y, Wagner H, Wolf A. From biokinematics to a robotic active vision system. Bioinspir Biomimet. 2017;12(5):056004.

    Article  Google Scholar 

  10. Atanasov N, Sankaran B, Le Ny J, Pappas GJ, Daniilidis K. Nonmyopic view planning for active object classification and pose estimation. IEEE Trans Robot. 2014;30(5):1078–90.

    Article  Google Scholar 

  11. Potthast C, Sukhatme GS. Next best view estimation with eye in hand camera. In: IEEE/RSJ intl. conf. on intelligent robots and systems (IROS). Citeseer; 2011.

  12. Potthast C, Sukhatme GS. A probabilistic framework for next best view estimation in a cluttered environment. J Vis Commun Image Rep. 2014;25(1):148–64.

    Article  Google Scholar 

  13. Doumanoglou A, Kouskouridas R, Malassiotis S, Kim T-K. Recovering 6d object pose and predicting next-best-view in the crowd. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 3583–3592.

  14. Rebull Mestres J. Implementation of an automated eye-in hand scanning system using best-path planning. Master’s thesis, Universitat Politècnica de Catalunya. 2017.

  15. Bircher A, Kamel M, Alexis K, Oleynikova H, Siegwart R. Receding horizon “ next-best-view” planner for 3d exploration. In: 2016 IEEE International conference on robotics and automation (ICRA). IEEE; 2016. p. 1462–1468.

  16. Lehnert C, Tsai D, Eriksson A, McCool C. 3d move to see: multi-perspective visual servoing towards the next best view within unstructured and occluded environments. In: 2019 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE; 2019. p. 3890–3897.

  17. Cui J, Wen JT, Trinkle J. A multi-sensor next-best-view framework for geometric model-based robotics applications. In: 2019 International conference on robotics and automation (ICRA). IEEE; 2019. p. 8769–8775.

  18. Jia Z, Chang Y-J, Chen T. A general boosting-based framework for active object recognition. In: British machine vision conference (BMVC). Citeseer; 2010. p. 1–11.

  19. Edmonds M, Yigit T, Yi J. Auto-calibrated 3d hyperspectral scanning using a heterogeneous set of cameras and lights with spectrally-optimal next-best-view planning. In: 2020 IEEE 16th international conference on automation science and engineering (CASE). IEEE; 2020. p. 863–868.

  20. Xu Y, Hu J, Wattanachote K, Zeng K, Gong Y. Sketch-based shape retrieval via best view selection and a cross-domain similarity measure. IEEE Trans Multimedia. 2020;22(11):2950–62.

    Google Scholar 

  21. Lauri M, Pajarinen J, Peters J, Frintrop S. Multi-sensor next-best-view planning as matroid-constrained submodular maximization. IEEE Robot Autom Lett. 2020;5(4):5323–30.

    Article  Google Scholar 

  22. Morrison D, Corke P, Leitner J. Multi-view picking: next-best-view reaching for improved grasping in clutter. In: 2019 International conference on robotics and automation (ICRA). IEEE; 2019. p. 8762–8768.

  23. Almadhoun R, Abduldayem A, Taha T, Seneviratne L, Zweiri Y. Guided next best view for 3d reconstruction of large complex structures. Remote Sens. 2019;11(20):2440.

    Article  Google Scholar 

  24. Palomeras N, Hurtós N, Vidal E, Carreras M. Autonomous exploration of complex underwater environments using a probabilistic next-best-view planner. IEEE Robot Automat Lett. 2019;4(2):1619–25.

    Article  Google Scholar 

  25. Gonzalez RC, Woods RE. Digital image processing. 4th ed. London: Pearson; 2018.

    Google Scholar 

  26. Ammirato P, Poirson P, Park E, Košecká J, Berg AC. A dataset for developing and benchmarking active vision. In: 2017 IEEE international conference on robotics and automation (ICRA). IEEE; 2017. p. 1378–1385.

Download references

Acknowledgements

This work has been supported in part by the Office of Naval Research award N00014-16-1-2312 and US Army Research Laboratory (ARO) award W911NF-20-2-0084.

Funding

This work has been supported in part by the Office of Naval Research award N00014-16-1-2312 and US Army Research Laboratory (ARO) award W911NF-20-2-0084.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA

    Pourya Hoseini, Shuvo Kumar Paul, Mircea Nicolescu & Monica Nicolescu

  2. Department of Ophthalmology, University of California, San Diego, CA, USA

    Pourya Hoseini

Authors
  1. Pourya Hoseini
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shuvo Kumar Paul
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mircea Nicolescu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Monica Nicolescu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization: PH, MN, MN; methodology: PH, MN, SKP; formal analysis and investigation: PH, MN, MN; writing—original draft preparation: PH; writing—review and editing: PH, SKP, MN; funding acquisition: MN, MN; resources: MN, MN, PH, SKP; supervision: MN, MN.

Corresponding author

Correspondence to Pourya Hoseini.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Ethics approval

Not applicable.

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the topical collection “Computer Vision, Imaging and Computer Graphics Theory and Applications” guest edited by Jose Braz, A. Augusto Sousa, Alexis Paljic, Christophe Hurter and Giovanni Maria Farinella.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hoseini, P., Paul, S.K., Nicolescu, M. et al. Next Best View Planning in a Single Glance: An Approach to Improve Object Recognition. SN COMPUT. SCI. 4, 51 (2023). https://doi.org/10.1007/s42979-022-01454-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-022-01454-w

Keywords

Search

Navigation