Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon openaccess Multi-target tracking of birds in complex low-altitude airspace based on GM_PHD filter

  • Author(s): Tao Hong 1 ; Wu Zhang 1 ; Weishi Chen 2 ; Xiaolong Chen 3 ; Xinru Fu 1
    • View affiliations
  • Source: Volume 2019, Issue 21, November 2019, p. 7672 – 7676
    DOI:  10.1049/joe.2019.0746 , Online ISSN 2051-3305
This is an open access article published by the IET under the Creative Commons Attribution -NonCommercial License (http://creativecommons.org/licenses/by-nc/3.0/)
Received 26/02/2019, Accepted 02/05/2019, Published 13/08/2019

GM_PHD (Gaussian mixture of probability hypothesis density) cannot completely track multiple targets, such as the flying birds in the complex low-altitude airspace near the airport, due to the lack of the steps of birth detection, track extraction and death detection. A new algorithm is proposed to solve this problem, which mainly contributes to the following three aspects. First, the k-nearest neighbour algorithm is used to detect the birth of bird targets from measurements which is necessary to construct the birth intensity function. Second, the clustering algorithm is introduced into the probability hypothesis density filter framework to extract the bird targets’ tracks from the filtering results. Third, an algorithm is added to detect the death of bird targets for better tracking. The Gaussian mixture implementation of the algorithm denoted as BT_GM_PHD (Bird Tracking GM_PHD) is presented. The test results on simulation and ground-truth data show that the proposed BT_GM_PHD algorithm can effectively track the multiple flying bird targets in the complex low-altitude airspace near the airport, outperforming the GM_PHD filter.

Inspec keywords: pattern clustering; nearest neighbour methods; radar imaging; radar tracking; filtering theory; Gaussian processes; mixture models; air safety; probability; target tracking; feature extraction

Other keywords: filtering results; complex low-altitude airspace; Gaussian mixture of probability hypothesis density; filter framework; BT_GM_PHD algorithm; multiple flying bird targets; k-nearest neighbour algorithm; death detection; track extraction; Gaussian mixture implementation; clustering algorithm; birth detection; GM_PHD filter; flying birds; birth intensity function; Bird Tracking GM_PHD algorithm; airport; multitarget tracking

Subjects: Filtering methods in signal processing; Optical, image and video signal processing; Other topics in aerospace; Other topics in statistics; Radar equipment, systems and applications

References

    1. 1)
      • 12. Huansheng, N., Weishi, C., Jing, L.: ‘Radar target tracking in cluttered environment based on particle filtering’, Aeronaut. J., 2010, 114, (1155), pp. 309–314.
    2. 2)
      • 5. ‘The bird attack aircraft information analysis report in 2015 (China Civil Aviation Academy of Science and Technology, Beijing, China 2016)’.
    3. 3)
      • 16. Huansheng, N., Jiakang, W., Weishi, C.: ‘Lévy-flight-based real-time bird-strike risk assessment for airports’, J. Risk. Res., 2013, 121, (1), pp. 1–9.
    4. 4)
      • 4. ‘The bird attack aircraft information analysis report in 2014 (China Civil Aviation Academy of Science and Technology, Beijing, China 2015)’.
    5. 5)
      • 18. Huansheng, N., Weishi, C.: ‘Bird strike risk evaluation at airports’, Aircr. Eng. Aerosp. Technol., 2014, 86, (2), pp. 129–137.
    6. 6)
      • 13. Huansheng, N., Weishi, C., Jing, L., et al: ‘Bird-aircraft strike avoidance radar’, IEEE Aerosp. Electron. Syst. Mag., 2010, 25, (1), pp. 19–28.
    7. 7)
      • 15. Jiakang, W., Huansheng, N., Weishi, C., et al: ‘Airport bird-strike risk assessment model with grey clustering evaluation method’, Chin. J. Electron., 2012, 21, (3), pp. 409–413.
    8. 8)
      • 6. Mahler, R.: ‘‘Statistics 102’ for multisource-multitarget detection and tracking’, IEEE. J. Sel. Top. Signal Process., 2013, 7, (3), pp. 376–389.
    9. 9)
      • 1. Li, Y., Shi, X.: ‘Investigation of the present status of research on bird impacting on commercial airplanes’, Acta Aeronaut. Astroncat. Sinica, 2012, 33, (2), pp. 189–198.
    10. 10)
      • 8. Mahler, R.: ‘Multitarget Bayes filtering via first-order multitarget moments’, IEEE Trans. Aerosp. Electron. Syst. (S00189251), 2003, 39, (3), pp. 1152–1178.
    11. 11)
      • 3. ‘The bird attack aircraft information analysis report in 2013 (China Civil Aviation Academy of Science and Technology, Beijing, China 2014)’.
    12. 12)
      • 9. Mahler, R.: ‘A theory of PHD filters of higher order in target number’. Signal Processing, Sensor Fusion, and Target Recognition XV, Proc. of SPIE, 62350K, Chiang Mai, Thailand, 2007, 6235, pp. 1523–1543.
    13. 13)
      • 14. Weishi, C., Huansheng, N., Jing, L.: ‘Flying bird detection and hazard assessment for avian radar system’, J. Aerosp. Eng., 2012, 25, (2), pp. 246–255.
    14. 14)
      • 17. Weishi, C., Huansheng, N.: ‘Edge clutter rejection for PPI radar images’, Aircr. Eng. Aerosp. Technol., 2014, 86, (1), pp. 19–25.
    15. 15)
      • 11. Zhu, Y.: ‘Research on multitarget tracking technology of radar emitter based on PHD filter’. PhD thesis, National University of Defense Technology, 2015.
    16. 16)
      • 7. Mahler, R.: ‘Statistical multisource-multitarget information fusion’ (Artech House, London, UK, 2007).
    17. 17)
      • 2. ‘Bird surveying radar makes airport ‘clinking eyes’ brighter’, Liberation Army Daily, 2017, p. 1.
    18. 18)
      • 10. Vo, B.N., Ma, W.K.: ‘Probability hypothesis density filter’, IEEE Trans. Signal Process., 2006, 54, (11), pp. 4091–4104.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2019.0746
Loading

Related content

content/journals/10.1049/joe.2019.0746
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address