Explicit Image Quality Detection Rules for Functional Safety in Computer Vision

Johann Thor Mogensen Ingibergsson, Dirk Kraft, Ulrik Pagh Schultz


Computer vision has applications in a wide range of areas from surveillance to safety-critical control of autonomous robots. Despite the potentially critical nature of the applications and a continuous progress, the focus on safety in relation to compliance with standards has been limited. As an example, field robots are typically dependent on a reliable perception system to sense and react to a highly dynamic environment. The perception system thus introduces significant complexity into the safety-critical path of the robotic system. This complexity is often argued to increase safety by improving performance; however, the safety claims are not supported by compliance with any standards. In this paper, we present rules that enable low-level detection of quality problems in images and demonstrate their applicability on an agricultural image database. We hypothesise that low-level and primitive image analysis driven by explicit rules facilitates complying with safety standards, which improves the real-world applicability of existing proposed solutions. The rules are simple independent image analysis operations focused on determining the quality and usability of an image.


  1. Adam, M., Larsen, M., Jensen, K., and Schultz, U. (2016). Rule-based dynamic safety monitoring for mobile robots. Journal of Software Engineering for Robotics, 7(1):121-141.
  2. Bansal, A., Farhadi, A., and Parikh, D. (2014). Towards transparent systems: Semantic characterization of failure modes. In Computer Vision-ECCV 2014, pages 366-381. Springer.
  3. Barry, A. J., Majumdar, A., and Tedrake, R. (2012). Safety verification of reactive controllers for uav flight in cluttered environments using barrier certificates. In International Conference on Robotics and Automation (ICRA), pages 484-490. IEEE.
  4. Bensalem, S., da Silva, L., Gallien, M., Ingrand, F., and Yan, R. (2010). Verifiable and correct-by-construction controller for robots in human environments. In seventh IARP workshop on technical challenges for dependable robots in human environments (DRHE).
  5. Blas, M. R. and Blanke, M. (2011). Stereo vision with texture learning for fault-tolerant automatic baling. Computers and electronics in agriculture, 75(1):159-168.
  6. Carlson, J., Murphy, R. R., and Nelson, A. (2004). Followup analysis of mobile robot failures. In International Conference on Robotics and Automation (ICRA), volume 5, pages 4987-4994. IEEE.
  7. Cheng, H. (2011). The State-of-the-Art in the USA. In Autonomous Intelligent Vehicles, pages 13-22. Springer.
  8. Daigle, M. J., Koutsoukos, X. D., and Biswas, G. (2007). Distributed diagnosis in formations of mobile robots. IEEE Transactions on Robotics, 23(2):353-369.
  9. Davis, J. and Goadrich, M. (2006). The relationship between precision-recall and roc curves. In Proceedings of the 23rd international conference on Machine learning, pages 233-240.
  10. De Cabrol, A., Garcia, T., Bonnin, P., and Chetto, M. (2008). A concept of dynamically reconfigurable realtime vision system for autonomous mobile robotics. International Journal of Automation and Computing, 5(2):174-184.
  11. Dollár, P., Belongie, S., and Perona, P. (2010). The fastest pedestrian detector in the west. In Proc. BMVC, pages 68.1-11.
  12. Gupta, P., Loparo, K., Mackall, D., Schumann, J., and Soares, F. (2004). Verification and validation methodology of real-time adaptive neural networks for aerospace applications. In International Conference on Computational Intelligence for Modeling, Control, and Automation.
  13. Ingibergsson, J. T. M., Schultz, U. P., and Kuhrmann, M. (2015). On the use of safety certification practices in autonomous field robot software development: A systematic mapping study. In Product-Focused Software Process Improvement, pages 335-352. Springer.
  14. Kurd, Z. and Kelly, T. (2003). Establishing safety criteria for artificial neural networks. InKnowledge-Based Intelligent Information and Engineering Systems, pages 163-169. Springer.
  15. Kurd, Z., Kelly, T., and Austin, J. (2003). Safety criteria and safety lifecycle for artificial neural networks. In Proc. of Eunite, volume 2003.
  16. Lucas, B. D., Kanade, T., et al. (1981). An iterative image registration technique with an application to stereo vision. In IJCAI, volume 81, pages 674-679.
  17. Mekki-Mokhtar, A., Blanquart, J.-P., Guiochet, J., Powell, D., and Roy, M. (2012). Safety trigger conditions for critical autonomous systems. In 18th Pacific Rim International Symposium on Dependable Computing, pages 61-69. IEEE.
  18. Mitka, E., Gasteratos, A., Kyriakoulis, N., and Mouroutsos, S. G. (2012). Safety certification requirements for domestic robots. Safety science, 50(9):1888-1897.
  19. Murphy, R. R. and Hershberger, D. (1999). Handling sensing failures in autonomous mobile robots. The International Journal of Robotics Research, 18(4):382- 400.
  20. Nguyen, A., Yosinski, J., and Clune, J. (2015). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 427-436. IEEE.
  21. Saito, T. and Rehmsmeier, M. (2015). The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets. In PLoS ONE, pages 1-21.
  22. Santosuosso, A., Boscarato, C., Caroleo, F., Labruto, R., and Leroux, C. (2012). Robots, market and civil liability: A european perspective. In RO-MAN, pages 1051-1058. IEEE.
  23. Schumann, J., Gupta, P., and Liu, Y. (2010). Application of neural networks in high assurance systems: A survey. In Applications of Neural Networks in High Assurance Systems, pages 1-19. Springer.
  24. Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2013). Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199.
  25. TC 127 (2015). Earth-moving machinery - autonomous machine system safety. International Standard ISO 17757-2015, International Organization for Standardization.
  26. TC 184 (2014). Robots and robotic devices - Safety requirements for personal care robots. International Standard ISO 13482:2014, International Organization for Standardization.
  27. TC 23 (2010). Tractors and machinery for agriculture and forestry - safety-related parts of control systems. International Standard ISO 25119-2010, International Organization for Standardization.
  28. TC 23 (2014). Agricultural machinery and tractors - Safety of highly automated machinery. International Standard ISO/DIS 18497, International Organization for Standardization.
  29. TC 23 (2015). Standards. International standard, International Organization for Standardization.
  30. TC 44 (2012). Safety of machinery - electro-sensitive protective equipment. International Standard IEC 61496- 2012, International Electronical Commission.
  31. Torralba, A. and Efros, A. A. (2011). Unbiased look at dataset bias. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 1521-1528. IEEE.
  32. Wang, R. and Bhanu, B. (2005). Learning models for predicting recognition performance. In Tenth IEEE International Conference on Computer Vision (ICCV), volume 2, pages 1613-1618. IEEE.
  33. Yang, L. and Noguchi, N. (2012). Human detection for a robot tractor using omni-directional stereo vision. Computers and Electronics in Agriculture, 89:116- 125.
  34. Zendel, O., Murschitz, M., Humenberger, M., and Herzner, W. (2015). Cv-hazop: Introducing test data validation for computer vision. In Proceedings of the IEEE International Conference on Computer Vision, pages 2066-2074.
  35. Zenke, D., Listner, D. J., and Author, A. (2016). Meeting on safety in sensor systems with employees from T ÜV NORD.
  36. Zhang, P., Wang, J., Farhadi, A., Hebert, M., and Parikh, D. (2014). Predicting failures of vision systems. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3566-3573.

Paper Citation

in Harvard Style

Ingibergsson J., Kraft D. and Pagh Schultz U. (2017). Explicit Image Quality Detection Rules for Functional Safety in Computer Vision . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 433-444. DOI: 10.5220/0006125604330444

in Bibtex Style

author={Johann Thor Mogensen Ingibergsson and Dirk Kraft and Ulrik Pagh Schultz},
title={Explicit Image Quality Detection Rules for Functional Safety in Computer Vision},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)},

in EndNote Style

JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)
TI - Explicit Image Quality Detection Rules for Functional Safety in Computer Vision
SN - 978-989-758-227-1
AU - Ingibergsson J.
AU - Kraft D.
AU - Pagh Schultz U.
PY - 2017
SP - 433
EP - 444
DO - 10.5220/0006125604330444