Generation of Three-Dimensional Synthetic Datasets
Main Article Content
Abstract
The work is devoted to the description of the process of developing a universal toolkit for generating synthetic data for training various neural networks. The approach used has shown its success and effectiveness in solving various problems, in particular, training a neural network to recognize shopping behavior inside stores through surveillance cameras and training a neural network for recognizing spaces with augmented reality devices without using auxiliary infrared cameras. Generalizing conclusions allow planning the further development of technologies for generating three-dimensional synthetic data.
Article Details
References
2. Heeger D.J. A model for the extraction of image flow // Proceedings of the Optical Society of America Topical Meeting on Computer Vision. 1987. P. 151–154.
3. Barron J.L., Fleet D.J., Beauchemin S.S. Performance of optical flow techniques // Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1992. P. 236–242.
4. McCane B., Novins K., Crannitch D., Galvin B. On benchmarking optical flow. // Computer Vision and Image Understanding. 2001. V. 84. P. 126–143.
5. Otte M., Nagel H.H. Estimation of optical flow based on higher-order spatiotemporal derivatives in interlaced and non-interlaced image sequences // Artificial Intelligence. 1995. V. 78. P. 5–43.
6. Meister S., Kondermann D. Real versus realistically rendered scenes for optical flow evaluation // 14th ITG Conference on Electronic Media Tech. 2011. P. 1–6.
7. Baker S., Roth S., Scharstein D., Black M.J., Lewis J.P., Szeliski R. A database and evaluation methodology for optical flow // IEEE 11th International Conference on Computer Vision. 2007. P. 1–8.
8. Vaudrey T., Rabe C., Klette R., Milburn J. Differences between stereo and motion behaviour on synthetic and real-world stereo sequences // 23rd International Conference Image and Vision Computing. 2008. P. 1–6.
9. Dwibedi D., Misra I., Hebert M. Cut, paste and learn: Surprisingly easy synthesis for instance detection // The IEEE International Conference on Computer Vision. 2017. P. 1–12.
10. Mac Aodha O., Brostow G.J., Pollefeys M. Segmenting video into classes of algorithm-suitability // IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2010. P. 1054–1061.
11. Butler D.J., Wulff J., Stanley G.B., Black M.J. A naturalistic open source movie for optical flow evaluation // ECCV 2012: Computer Vision – ECCV. 2012. P. 611–625.
12. Onkarappa N., Sappa A.D. Speed and texture: An empirical study on optical-flow accuracy in ADAS scenarios // IEEE Transactions on Intelligent Transportation Systems. 2014. V. 15. No. 1. P. 136–147.
13. Qiu W., Yuille A.L. UnrealCV: Connecting computer vision to Unreal Engine // Computer Vision – ECCV 2016. 2016. Workshops. P. 909–916.
14. Zhang Y., Qiu W., Chen Q., Hu X., Yuille A.L. UnrealStereo: A synthetic dataset for analyzing stereo vision // ArXiv Preprint arXiv:1612.04647. 2016. P. 1–10.
15. Taylor G.R., Chosak A.J., Brewer P.C. OVVV: Using virtual worlds to design and evaluate surveillance systems // 007 IEEE Conference on Computer Vision and Pattern Recognition. 2007. P. 1–8.
16. Dosovitskiy A., Ros G., Codevilla F., Lopez A., Koltun V. Carla: An open urban driving simulator // Conference on Robot Learning. 2016. P. 1–16.
17. Gaidon A., Wang Q., Cabon Y., Vig E. Virtual worlds as proxy for multi-object tracking analysis // IEEE Conference on Computer Vision and Pattern Recognition. 2016. P. 4340–4349.
18. Ros G., Sellart L., Materzynska J., Vazquez D., Lopez A.M. The Synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. P. 3234–3243.
19. Richter S.R., Hayder Z., Koltun V. Playing for benchmarks // International Conference on Computer Vision. 2017. Iss. 8237505.
20. Handa A., Pătrăucean V., Badrinarayanan V., Stent S., Cipolla R. Understanding realworld indoor scenes with synthetic data // IEEE Conference on Computer Vision and Pattern Recognition. 2016. Iss. 7780811. P. 4077–4085.
21. McCormac J., Handa A., Leutenegger S., Davison A.J. Scenenet RGB-D: Can 5m synthetic images beat generic imagenet pre-training on indoor segmentation? // The IEEE International Conference on Computer Vision. 2017. Iss. 8237554. P. 2697–2706.
22. Handa A., Whelan T., McDonald J., Davison A. A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM // IEEE International Conference on Robotics and Automation. 2014. Iss. 6907054. P. 1524–1531.
23. Song S., Yu F., Zeng A., Chang A.X., Savva M., Funkhouser T. Semantic scene completion from a single depth image // IEEE Conference on Computer Vision and Pattern Recognition. 2017. P. 190–198.
24. Wu Z., Song S., Khosla A., Yu F., Zhang L., Tang X., Xiao J. 3D shapenets: A deep representation for volumetric shapes // IEEE Conference on Computer Vision and Pattern Recognition. 2015. Iss. 7298801. P. 1912–1920.
25. Chang A.X., Funkhouser T., Guibas L., Hanrahan P., Huang Q., Li Z., Savarese S., Savva M., Song S., Su H., Xiao J., Yi L., Yu F. ShapeNet: An Information-Rich 3D Model Repository // Tech. Rep. ArXiv preprint arXiv:1512.03012. 2015.
26. de Souza C.R., Gaidon A., Cabon Y., Peña A.M.L. Procedural generation of videos to train deep action recognition networks // 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017. P. 2594–2604
27. Su H, Qi C.R., Li Y., Guibas L.J. Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3D model views // IEEE International Conference on Computer Vision. 2015. Iss. 7410665. P. 2686–2694.
28. Movshovitz-Attias Y., Kanade T., Sheikh Y. How useful is photo-realistic rendering for visual learning? // ECCV Workshops. 2016. P. 1–16.
29. Zhang Y., Song S., Yumer E., Savva M., Lee J.Y., Jin H., Funkhouser T. Physically-based rendering for indoor scene understanding using convolutional neural networks // IEEE Conference on Computer Vision and Pattern Recognition. 2017. P. 5057–5065.
30. Абдурайимов Л.Н., Халилова З.Э. Краткий обзор популярных движков для создания игровых приложений под операционную систему Android // Информационно-компьютерные технологии в экономике, образовании и социальной сфере. 2018. С. 80–86.
31. Unreal Engine // URL: https://www.unrealengine.com/
32. Unity // URL: https://unity.com/
33. Magdics M., Sauvaget C., García R.J., Sbert M. Post-Processing NPR Effects for Video Games // 12th ACM International Conference on Virtual Reality Continuum and Its Applications in Industry (VRCAI). 2013. P. 147–156.
34. Metahuman Creator // URL: https://www.unrealengine.com/en-US/digital-humans
35. Кугуракова В.В., Зыков Е.Ю., Касимов А.В., Ситдиков А.Г., Скобелев А.А., Шайхутдинова Е.Ф. In situ двухдиапазонная 3D-дефектоскопия стенописей архитектурных памятников // Электронные библиотеки. 2016. T. 19. №6. C. 538–558.
36. Тарасов А.С., Кугуракова В.В. Реконструкция трехмерной модели человека по единственному изображению // Электронные библиотеки. 2021. Т. 24, № 3. С. 485–504.
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.