Application of the Kalman filter in tracking problems of air objects

Authors: Pimenova M.B.
Published in issue: #12(41)/2019
DOI: 10.18698/2541-8009-2019-12-557
Category: Informatics, Computer Engineering and Control | Chapter: System Analysis, Control, and Information Processing, Statistics
Keywords: Kalman filter, video sequence frame processing, object tracking, image segmentation, machine vision, video stream, object capture
Published: 19.12.2019

The algorithm is considered of capturing and subsequent tracking of an air object in the survey using the Kalman filter. This algorithm allows you to track an object moving within the scene along a previously unknown path, also thanks to the built-in forecast/correction system, it makes it possible to predict the location of the object at a subsequent point in time. The development of effective algorithms for applying the Kalman filter in tracking tasks of moving objects is one of the fundamental directions in the field of computer vision. The algorithm considered in this paper selects the desired object on the scene, displays the current trajectory of the aircraft, adapts to the possible maneuver of the object at an arbitrary point in time or to its disappearance with the subsequent appearance on the scene. The synthesized trajectory of the air object movement is visualized. To increase the speed of the algorithm, it is possible to configure the detection parameters and the threshold for image segmentation. The results of the experiments confirm the effectiveness of using the Kalman filter in the tasks of restoring the trajectory of an object overlapping by objects of the foreground of the scene.

References

[1] Mokshin V.V., Kirpichnikov A.P., Sharnin L.M. Object tracking in video stream by significant features based on particles filtration. Vestnik Kazanskogo tekhnologicheskogo universiteta, 2013, no. 18, pp. 298–303 (in Russ.).

[2] Viola P., Jones M.J. Rapid object detection using a boosted cascade of simple features. IEEE CVPR, 2001, vol. 1, pp. 511–518. DOI: 10.1109/CVPR.2001.990517 URL: https://ieeexplore.ieee.org/document/990517

[3] Zabegaev A.N., Pavlovskiy V.E. Kalman filter adaptation for use with local and global navigation system. Preprinty IPM im. M.V. Keldysha [KIAM Preprint], 2010, no. 82 (in Russ.).

[4] Moroz A.N., Khmarskiy P.A., Shaban S.A., et al. The comparative analysis of unscented and extended Kalman filterS for global positioning systems receiver data processing. Doklady BGUIR, 2014, no. 4(82), pp. 66–72 (in Russ.).

[5] Porshakov A.S, Ponomarenko A.A., Sinyakov A.A. Assessment and forecasting of Russian GDP by means of dynamic factor model. Zhurnal Novoy ekonomicheskoy assotsiatsii, 2016, no. 2(30), pp. 60–76. DOI: 10.31737/2221-2264-2016-30-2-3 URL: http://www.econorus.org/repec/journl/2016-30-60-76r.pdf (in Russ.).

[6] Volosatova T.M., Yablokov V.E. Tracking of selected object through the video sequence. Inzhenernyy vestnik [Engineering Bulletin], 2015, no. 7. URL: http://engsi.ru/doc/789966.html (in Russ.).

[7] Kaspers A. Blob detection. Image Science Institute, UMC Utrecht, Tech. Rep., 2011.

[8] Bochem A., Herpers R., Kent K.B. Hardware acceleration of blob detection for image processing. 3rd Int. Conf. Advances in Circuits, Electronics and Micro-Electronics, 2010, pp. 28–33. DOI: 10.1109/CENICS.2010.12 URL: https://ieeexplore.ieee.org/document/5558171

[9] Agafonov V.Yu., Rozaliev V.L., Zaboleeva-Zotova A.V. Using of the Kalman filter in problems of object tracking. Intellektual’nye sistemy. Teoriya i prilozheniya, 2016, vol. 20, no. 4, pp. 13–17 (in Russ.).

[10] Zakharova M.V., Shmigel’skiy G., Grigor’yev V.V. Study of computer vision algorithms for space tracking systems in typical modes of their functioning. Nauchno-tekhnicheskiy vestnik informatsionnykh tekhnologiy, mekhaniki i optiki [Scientific and technical journal of information technologies, mechanics and optics], 2018, vol. 18, no. 3, pp. 487–492 (in Russ.).

[11] Lowe D.G. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 2004, vol. 60, no. 2, pp. 91–110. DOI: 10.1023/B:VISI.0000029664.99615.94 URL: https://link.springer.com/article/10.1023%2FB%3AVISI.0000029664.99615.94

[12] Dyshlyuk V.O. Study on quality figures and speed of datum point search at the images by SURF method. Molodoy uchenyy [Young Scientist], 2018, no.27, pp. 23–26 (in Russ.).

[13] Popov Yu.B., Masharov K.V. The estimation of the coordinates of an aerial object in multi-station radars with the usage of Kalman filter. Doklady TUSUR [Proceedings of TUSUR University], 2011, no. 1(23), pp. 22–28 (in Russ.).