OBJECT DETECTION METHOD APPLICATION TO RUNWAY IMAGERY IN LOW VISIBILITY CONDITIONS
https://doi.org/10.32603/1993-8985-2019-22-1-17-28
Abstract
When ensuring aviation safety, the outboard environment awareness of the crew in low visibility conditions is especially important. The information about the runway condition and availability of any obstacles is crucial. There are ground-based obstacle detection systems, but currently only large airports are equipped with them. There are Enhanced Vision Systems designed for application on aircraft in low visibility conditions. The main goal of this research is to develop the means of runway obstacle recognition in low visibility conditions, which are to improve the capabilities of Enhanced Vision Systems. The research covers only the methods for static image object detection. The analysis of the runway markings, objects and possible obstacles is performed. Targets for acquisition are defined. The simulation of runway images is performed on full-flight simulator in low visibility conditions. The requirements for features descriptors, recognition and detection methods are defined and methods for research are defined. The paper provides evaluation of method applicability to runway pictures taken in poor visibility conditions above and below the decision height taking into account various characteristics. The covered methods solve the problem of detecting objects of the runway in low visibility conditions for static image. Conclusions about the possibility to use the studied methods in Enhanced Vision Systems are made. Further development of optimization methods is required to perform detection in video sequences in real time. The results of this work are relevant to the tasks of avionics, computer vision and image processing.
About the Author
D. S. AndreevRussian Federation
References
1. Vizilter Yu. V., Zheltov S. Yu. Problemy tekhnicheskogo zreniya v sovremennykh aviatsionnykh sistemakh [Problems of Technical Vision in Modern Aviation Systems]. Proceedings of Scientific and Technical Conference-Seminar “Technical Vision in Mobile Object Management Systems - 2010”, Tarusa, 16–18 March 2010. Ed. by R. R. Nazirov. Moscow, University Book House, 2011, vol. 4, pp. 11–44. (In Russian)
2. U.S. Federal Aviation Administration. Advisory circular on Airport Foreign Object Debris (FOD) Detection Equipmen. 2009. Available at: https://www.faa.gov/documentLibrary/media/Advisory_Circular/150_5210_24.pdf (accessed 10.02.2019)
3. Weller J. R. FOD Detection System. Evaluation, Performance Assessment and Regulatory Guidance. Wildlife and Foreign Object Debris (FOD). Workshop, Cairo, Egypt, 24–26 March, 2014. Available at: https://www.icao.int/MID/Documents/2014/Wildlife%20a nd%20FOD%20Workshop /Assessing%20Risk%20FAA.pdf (accessed 10.02.2019)
4. Sokolova M. A. Sistemy upravleniya nazemnym dvizheniem na ploshchadi manevrirovaniya aerodroma [Ground Movement Control Systems at Aerodrome Maneuvering Area]. Sovremennye innovatsii [Modern Innovations], 2018, vol. 26, no. 4, pp. 26–27. (In Russian)
5. Kostyashkin L. N, Loginov A. A., Nikiforov M. B. Problem Aspects of a Combined Aircraft Vision System. Izvestiya SFedU [Proceedings of the Southern Federal University. Engineering Sciences], 2013, no. 5, pp. 61–65. (In Russian)
6. Airport Services Manual. Pt. 6. Controlling obstacles. Guide Doc 9137-AN/898/2, 1983. Available at: http://files.repuloterek-civil-katonai-kozos.webnode.hu/ 200000025-66bfa67b8d/Doc_9137_P6_CONTROL%20OF% 20OBSTACLES.pdf (accessed 30.01.2019)
7. Aviation rules. Pt. 139. Certification of Airfields. Title 14, Code of Federal Regulations (CFR). 2004. Available at: https://www.govinfo.gov/content/pkg/CFR-2014-title14-vol3 /pdf/CFR-2014-title14-vol3-part139.pdf (accessed 10.02.2019)
8. Dalal N., Triggs B. Histograms of Oriented Gradients for Human Detection. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, 20–25 June 2005. Piscataway, IEEE, 2005. doi: 10.1109/CVPR.2005.177
9. Vapnik V. N. Vosstanovlenie zavisimostei po empiricheskim dannym [Dependency Recovery Based on Empirical Data]. Мoscow, Nauka, 1979, 448 p. (In Russian)
10. Cristianini N., Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. NY: Cambridge University Press, 2000. 168 p. doi: 10.1017/CBO9780511801389
11. Cover T. M., Hart P. E. Nearest Neighbor Pattern Classification // IEEE Trans. on Information Theory. 1967, vol. IT-13, iss. 1, pp. 21–27. doi: 10.1109/TIT.1967.1053964
12. Dudani S. A. The Distance-Weighted k-Nearest-Neighbor Rule. IEEE Transactions on Systems, Man, and Cybernetics. 1976, vol. 6, iss. 4, pp. 325–327. doi: 10.1109/TSMC.1976.5408784
13. Quinlan J. R. Induction of Decision Trees. Machine Learning. 1986, vol. 1, iss. 1, pp. 81–106.
14. Barla A., Odone F., Verri A. Histogram Intersection Kernel for Image Classification. 2003 Intern. Conf. on Image Processing, Barcelona, Spain. IEEE, 2003. doi: 10.1109 /ICIP.2003.1247294
15. Andelson E. H., Anderson C. H., Bergen J. R., Burt P. J., Ogden J. M. Pyramid Methods in Image Processing. RCA Engineer. 1984, vol. 29, iss. 6, pp. 33–41. Available at: http://persci.mit.edu/pub_pdfs/RCA84.pdf (accessed 10.02.2019)
16. Glumov N. I., Kolomiyetz E. I., Sergeyev V. V. Detection of Objects on the Image Using a Sliding Window Mode. Optics & Laser Technology. 1995, vol. 27, Iss. 4, pp. 241–249. doi: 10.1016/0030-3992(95)93752-D
17. Wilkinson L., Friendly M. The History of the Cluster Heat Map. The American Statistician. 2009, vol. 63, no. 2, pp. 179–184. doi: 10.1198/tas.2009.0033
18. Powers D. M. W. Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation. Journal of Machine Learning Technologies. 2011, vol. 2, no. 1, pp. 37–63.
19. Andreev D. S., Lysenko N. V. Preprocessing Methods for Runway Pictures Taken in Poor Visibility Conditions. 2018 IEEE Conf. of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), Saint-Petersburg, Russia. IEEE, 2018. doi: 10.1109/EIConRus. 2018.8317273
20. Xiaobin L., Wang S. Object Detection Using Convolutional Neural Networks in a Coarse-to-Fine Manner. IEEE Geoscience and Remote Sensing Letters. 2017, vol. 14, iss. 11. doi: 10.1109/LGRS.2017.2749478
Review
For citations:
Andreev D.S. OBJECT DETECTION METHOD APPLICATION TO RUNWAY IMAGERY IN LOW VISIBILITY CONDITIONS. Journal of the Russian Universities. Radioelectronics. 2019;(1):17-28. (In Russ.) https://doi.org/10.32603/1993-8985-2019-22-1-17-28