SavedAdd your journal

Journals / Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi / 2022 / Cilt: 30 - Sayı: 3

DEVELOPMENT OF A FAULT INJECTION TOOL & DATASET FOR VERIFICATION OF CAMERA BASED PERCEPTION IN ROBOTIC SYSTEMS

ROBOTİK SİSTEMLERDE KAMERA TABANLI ALGININ DOĞRULANMASI İÇİN HATA ENJEKSİYON ARACI VE VERİ KÜMESİNİN GELİŞTİRİLMESİ

Uğur YAYAN
Alim Kerem ERDOĞMUŞ
Pages
328–339
Publication Date
2022-12-21
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)

Also, a fault injected image dataset created by CamFITool for verification of camera-based perception studies in robotic systems is given.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Nowadays, camera-based perception is most popular topic in robotic systems.
📊
Key Findings & Data:Verification of camera-based perception systems are crucial and difficult with current tools and methods.
💡
Conclusion & Impact:Also, a fault injected image dataset created by CamFITool for verification of camera-based perception studies in robotic systems is given.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:robotik · doğrulama · hata enjeksiyonu

Abstract

Nowadays, camera-based perception is most popular topic in robotic systems. Verification of camera-based perception systems are crucial and difficult with current tools and methods. This study proposes Camera Fault Injection Tool (CamFITool), which enables different kind of fault injection methods to RGB and TOF cameras in order to perform verification and validation activities on robotic systems. Besides, Fault Injected Image Database which is created by CamFITool is introduced. In addition, the study guides to readers to create new datasets by injecting faults into existing image libraries or camera streams with CamFITool. As a result, CamFITool, an open-source fault injection tool, which is a critical tool for assessing of fault tolerant systems’ safety and security, is proposed. Also, a fault injected image dataset created by CamFITool for verification of camera-based perception studies in robotic systems is given.

Özet

Günümüzde robotik sistemlerde kamera tabanlı algılama en popüler konulardan biridir. Mevcut araç ve yöntemlerle kamera tabanlı algılama sistemlerinin doğrulanması da çok önemli ve zordur. Bu çalışma, robotik sistemlerde doğrulama ve onaylama faaliyetlerini gerçekleştirmek için RGB ve TOF kameralara farklı türlerde hata enjeksiyon yöntemleri sağlayan Kamera Hatası Enjeksiyon Aracını (CamFITool) önermektedir. Ayrıca CamFITool tarafından oluşturulan hata enjekte edilmiş imge kümesi tanıtılmaktadır. Buna ek olarak çalışma, CamFITool ile mevcut görüntü kitaplıklarına veya kamera akışlarına hatalar enjekte ederek yeni imge kümeleri oluşturmak için okuyuculara rehberlik edilmektedir. Sonuç olarak, hataya dayanıklı sistemlerin emniyet ve güvenliğini değerlendirmek için kritik bir araç olan açık kaynaklı hata enjeksiyon aracı CamFITool önerilmiştir. Ayrıca robotik sistemlerde kamera tabanlı algılama çalışmalarının doğrulanması için CamFITool tarafından oluşturulan hata enjekte edilmiş görüntü veri kümesi verilmiştir.

🔖

Cite This Article

YAYAN, U., ERDOĞMUŞ, A. K. (2022). DEVELOPMENT OF A FAULT INJECTION TOOL & DATASET FOR VERIFICATION OF CAMERA BASED PERCEPTION IN ROBOTIC SYSTEMS. Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi, Cilt: 30 - Sayı: 3, 328–339. https://ajindex.com/articles/867953

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (2)

  1. Referans1 Osadcuks, V., Pudzs, M., Zujevs, A., Pecka, A., & Ardavs, A. (2020, May). Clock-based time sync hronization for an event-based camera dataset acquisition platform. In 2020 IEEE International Conference on Robotics and Automation (ICRA) (pp. 4695-4701). IEEE. Referans2 Kendall, A., Grimes, M., & Cipolla, R. (2015). Posenet: A convolutional network for real-time 6-dof camera relocalization. In Proceedings of the IEEE international conference on computer vision (pp. 2938-2946). Referans3 Park, H., & Mu Lee, K. (2017). Joint estimation of camera pose, depth, deblurring, and super-resolution from a blurred image sequence. In Proceedings of the IEEE International Conference on Computer Vision (pp. 4613-4621). Referans4 Anomaly Detection, A Key Task for AI and Machine Learning, Explained. [Online]. Available: https://www.kdnuggets.com/2019/10/anomaly-detection-explained.html (2021) Referans5 Scharr, H., Minervini, M., Fischbach, A., & Tsaftaris, S. A. (2014, July). Annotated image datasets of rosette plants. In European Conference on Computer Vision. Zürich, Suisse (pp. 6-12). Referans6 Rezazadegan, F., Shirazi, S., Upcrofit, B., & Milford, M. (2017, May). Action recognition: From static datasets to moving robots. In 2017 IEEE International Conference on Robotics and Automation (ICRA) (pp. 3185-3191). IEEE. Referans7 Su, C., Zhang, S., Xing, J., Gao, W., & Tian, Q. (2016, October). Deep attributes driven multi-camera person re-identification. In European conference on computer vision (pp. 475-491).
  2. Springer, Cham. Referans8 Per, J., Kenk, V. S., Kristan, M., & Kovacic, S. (2012, September). Dana36: A multi-camera image dataset for object identification in surveillance scenarios. In 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance (pp. 64-69). IEEE. Referans9 Wu, S., Oreifej, O., & Shah, M. (2011, November). Action recognition in videos acquired by a moving camera using motion decomposition of lagrangian particle trajectories. In 2011 International conference on computer vision (pp. 1419-1426). IEEE. Referans10 Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008). LabelMe: a database and web-based tool for image annotation. International journal of computer vision, 77(1-3), 157-173. Referans11 Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009, June). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (pp. 248-2