Uçan nesnelerin otomatik tespit ve takibi için yeni bir yaklaşım

Abstract

Bu çalışmada yerden havaya takip görevlerinde kullanılan video sistemlerinin uçan nesneleri otomatik olarak tespit ve takip etmesi için yeni bir metot sunulmaktadır. Bu yaklaşımda uçan bir nesnenin varlığının tespiti için Standart Sapma bilgisinin kullanıldığı bir metot geliştirilmiştir. Tespit sonrası takip için ölçüm verisi takibe uygun hale getirilir, bu amaçla uçan nesnenin arka fona göre daha baskın hale gelmesi sağlanır. Hedefin takibi için gerçek zamanlı performans verebilen genlik bilgisi ilave edilmiş Etkileşimli Çoklu Model Olasılıksal Veri İlişkilendirme (EÇMOVİ-GB) algoritması kullanılmıştır.  EÇMOVİ-GB algoritması temelde nokta verisi takibinde kullanılan bir algoritma olmakla birlikte bu çalışmada video takibinde kullanılabilirliği gösterilmiştir. Bu amaçla örneklenen video çerçevelerinin genlik bilgileri uygun olarak kodlanarak nokta verisi haline getirilir ve takip bu veri üzerinden gerçekleştirilir. Böylece hedefin otomatik olarak tespit edildiği, takibin başlatıldığı ve sürdürüldüğü bir algoritma geliştirilmiştir. Algoritma değişik manevra, hedef tipleri ve arka fon gürültü durumları için incelenerek, başarılı sonuçlar elde edilmiştir.

Keywords

• Otomatik hedef tespiti,Video takip,Etkileşimli çoklu model,Olasılıksal modelleme

A novel approach for automatic detection and tracking of flying objects

Abstract

In this study, a new method is presented to automatically detect and track flying objects through video systems that are used for surface to air tracking tasks. In this approach, a method has been developed in which Standard Deviation is used to determine the presence of a flying object. The measurement data is adapted to track, so that the flying object becomes more dominant than the background. In order to track the detected target in real time, Interacting Multiple Model Probabilistic Data Association with Amplitude Information (IMMPDA-AI) algorithm is used. Although the IMMPDA-AI algorithm is mainly a point tracking algorithm, in this study, its applicability to video tracking is shown. For this purpose, the amplitude information of the sampled video frames is encoded as point data and the tracking is performed on this data. Thus, an algorithm has been developed in which the target is automatically detected, track initiated and continued. The algorithm is evaluated for different maneuvers, target types and clutter situations, and successful results are obtained.

Keywords

• Automatic target detection,Video tracking,Interacting multiple model,Probabilistic data association

References

1. Cao X, Yang L, Guo X. "Total variation regularized RPCA for irregularly moving object detection under dynamic background". IEEE Transactions on Cybernetics, 46(4), 1014-1027, 2016.
2. Rozantsev A, Lepetit V, Fua P. “Detecting flying objects using a single moving camera”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(5), 879-892, 2017.
3. Chandran R, Raman N. “A review on video-based techniques for vehicle detection, tracking and behavior understanding”. International Journal of Advances in Computer and Electronics Engineering, 2(5), 07-13, 2017.
4. Xu Y, Dong J, Zhang B, Daoyun X. "Background modeling methods in video analysis: A review and comparative evaluation". CAAI Transactions on Intelligence Technology, 1(1), 43-60, 2016.
5. Chen M, Wei X, Yang Q, Li Q, Wang G, Yang MH. “Spatiotemporal GMM for background subtraction with superpixel hierarchy”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1518-1525, 2018.
6. Elharrouss O, Abbad A, Moujahid D, Riffi J, Tairi H. “A block-based background model for moving object detection”. Electronic Letters on Computer Vision and Image Analysis, 15(3), 17-31, 2016.
7. Maddelena L, Petrosino A. “Background subtraction for moving object detection in RGBD data: A survey”. Journal of Imaging, 4(5), 71, 2018.
8. Barron JL, Fleet DJ, Beauchemin SS. “Performance of optical flow techniques”. International Journal of Computer Vision, 12 (1), 43-77, 1994.

9. Colque RVHM, Caetano C, De Andrade MTL, Schwartz WR. “Histograms of optical flow orientation and magnitude and entropy to detect anomalous events in videos”. IEEE Transactions on Circuits and Systems for Video Technology, 27(3), 673-682, 2017.
10. Kroeger T, Timofte R, Dai D, Van Gool L. “Fast optical flow using dense inverse search”. Computer Vision-European Conference on Computer Vision (ECCV) 2016, Amsterdam, The Netherlands, 11-14 October 2016.
11. Zhang J, Ding Y, Xu H, Yuan Y. "An optical flow based moving objects detection algorithm for the UAV". IEEE 4th International Conference on Computer and Communication Systems, Singapore, 23-25 February 2019.
12. Singh G, Saha S, Sapienza M, Torr P, Cuzzolin F. “Online real-time multiple spatiotemporal action localisation and prediction”. International Conference on Computer Vision (ICCV 2017), Venice, Italy, 22-29 October 2017.
13. Liang R, Yan L, Gao P, Qian X, Zhang Z, Sun H. “Aviation video moving-target detection with inter-frame difference”. IEEE 3rd International Congress on Image and Signal Processing, Yantai, China, 16-18 October 2010.
14. Zhu M, Wang H. “Fast detection of moving object based on improved frame-difference method”. IEEE 2017 6th International Conference on Computer Science and Network Technology, Dalian, China, 21-23 October 2017.
15. Wei H, Peng Q. “A block-wise frame difference method for real-time video motion detection”. International Journal of Advanced Robotic Systems, 15(4), 1-13, 2018.
16. Shi G, Suo J, Liu C, Wan K, Lv X. "Moving target detection algorithm in image sequences based on edge detection and frame difference". IEEE 3rd Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 3-5 October 2017.
17. Pakfiliz AG. "Automatic detection of aerial vehicle in cloudy environment by using wavelet enhancement technique". Radioengineering, 26(4), 1169-1176, 2017.
18. Gonzalez RC, Woods RE. Digital Image Processing. 2nd ed. New Jersey, USA, Prentice Hall, 2001.
19. Han DS, Juan ROS, Jung MW, Cha HW, Kim HS. “Development of a novel fast rotation angle detection algorithm using a quasi-rotation ınvariant feature based on sobel edge”. Journal of Telecommunication, Electronic and Computer Engineering, 9(2-6), 33-36, 2017.
20. Bar-Shalom Y, Li XR. Multitarget-Multisensor Tracking: Principles and Techniques. Connecticut, USA, YBS Publishing, 1995.
21. Bar-Shalom Y, Li XR, Kirubarajan T. Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software. New York, USA, Wiley, 2001.
22. Rashid M, Sebt MA. “Tracking a maneuvering target in the presence of clutter by multiple detection radar and ınfrared sensor”. 2017 Iranian Conference on Electrical Engineering (ICEE), Tehran, Iran, 2-4 May 2017.
23. Gupta S, Mazumdar SG. “Sobel edge detection algorithm”. International Journal of Computer Science and Management Research, 2(2), 1578-1583, 2013.
24. Stone LD, Streit RL, Corwin TL, Bell KL. Bayesian Multiple Target Tracking. 2nd ed. MA, USA, Artech House, 2013.
25. Li X, Willett P, Baum M. and Y. Li, "PMHT approach for underwater bearing-only multisensory-multitarget tracking in clutter". Journal of Oceanic Engineering, 41(4), 831-839, 2016.
26. Efe M, Ruan Y, Willett P. “The pedestrian PMHT". Fifth International Conference on Information Fusion, Annapolis, MD, USA, 8-11 July 2002.