Journals / Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi / 2022 / Cilt: 28 - Sayı: 2

Direct pose estimation from RGB images using 3D objects

3 Boyutlu nesneleri kullanarak imgelerden poz kestirimi

Pages
277–285
Publication Date
2022-04-30
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Furthermore, we introduce a new synthetic dataset for demonstrating the proposed methods capabilities.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:We present a real-time monocular camera pose estimation algorithm for augmented reality applications.
📊
Key Findings & Data:Proposed model is a small convolutional neural network that is trained to directly estimate 6 Degree of Freedom (6-DOF) camera pose from an RGB image.
💡
Conclusion & Impact:Furthermore, we introduce a new synthetic dataset for demonstrating the proposed methods capabilities.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Arttırılmış Gerçeklik · Poz kestirimi · Derinöğrenme

Abstract

We present a real-time monocular camera pose estimation algorithm for augmented reality applications. Proposed model is a small convolutional neural network that is trained to directly estimate 6 Degree of Freedom (6-DOF) camera pose from an RGB image. Our model is designed to run on real-time devices with low memory and computation power. Our model can estimate the camera pose in less than 1ms while keeping accuracy comparable to the state-of-the art. This was made possible by employing geometrically sound loss functions and algebraic constraints. Furthermore, we introduce a new synthetic dataset for demonstrating the proposed methods capabilities.

Özet

Artırılmış gerçeklik uygulamalarında kullanılmak üzere tek bir kameradan bir nesnenin yön ve konum kestirimini yapan bir algoritma sunulmaktadır. Küçük bir konvolüsyon ağından oluşan bu model 6 serbestlik dereceli konum ve yön bilgisini tek bir KYM (kırmızı-mavi-yeşil) imgeden elde etmektedir. Önerilen model yüksek başarım ve hafıza içermeyen mobil cihazlar için idealdir. Algoritma verilen bir imgeyi 1ms içinde işlemekte ve güncel algoritmaların performansına yakın performans sergilemektedir. Önerilen geometrik kayıp fonksiyonu ve kullanılan cebirsel kısıtlamaları modelin performansını sağlamaktadır. Aynı zamanda sentetik bir veri kümesi de bu tür modellerin performansını ölçmek için önerilmiştir.

🔖

Cite This Article

DEDE, M. A., GENÇ, Y. (2022). Direct pose estimation from RGB images using 3D objects. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 28 - Sayı: 2, 277–285. https://ajindex.com/articles/394861

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (13)

  1. Kendall A, Grimes M, Cipolla R. “PoseNet: A convolutional network for real-time 6-DOF camera relocalization”. In Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Las Condes, Chile, 11-18 December 2015
  2. 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 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 23-28 June 2013
  3. Lin C. “Microsoft COCO: Common objects in context”. In the European Conference on Computer Vision (ECCV), Zurich, Switzerland, 14-21 August 2014
  4. Gao H, Zhuang L, Kilian QW. “Densely connected convolutional networks”. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 27-30 June 2016
  5. Zhou B, Lapedriza A, Khosla A, Oliva A, Torralba T. “Places: A 10 million image database for scene recognition”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1452-1464, 2018
  6. Martin A, Agarwal A, Barham A. “TensorFlow: Large-Scale machine learning on heterogeneous systems”. arXiv, 2016.
  7. Diederik P, Ba J. “Adam: A method for stochastic optimization” 3rd International Conference on Learning Representations, {ICLR} 2015, San Diego, USA, 7-9 May 2015
  8. Kehl W, Manhardt F, Tombari F, Ilic S, Navab N. “SSD-6D: making RGB-Based 3D detection and 6D pose estimation great again”. IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22-29 October 2017
  9. Tekin B, Sinha S, Fua P. “Real-Time seamless single shot 6D object pose prediction”. In the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 18-22 June 2018
  10. Wang H, Sridhar S, Huang J, Valentin J, Song S, Guibas L. “Normalized object coordinate space for category-level 6D object pose and size Estimation”. In the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 16-20 June 2019
  11. Sock J, In Kim K, Sahin C, Kyun Kim T.” Multi-Task deep networks for depth-based 6D object pose and joint registration in crowd scenarios” British Machine Vision Conference (BMVC), New Castle, UK, 3-6 November 2018
  12. Sundermeyer M, Marton ZC, Durner M, Brucker M, Triebel, R. “Implicit 3D orientation learning for 6D object detection from RGB images”. In the European Conference on Computer Vision (ECCV), Munich, Germany, 8-14 September 2018
  13. Oberw