Skip to main content
SpringerLink
Log in

Bidirectional feedback of optimized gaussian mixture model and kernel correlation filter for enhancing simple detection of small pixel vehicles

  • S.I.: AI based Techniques and Applications for Intelligent IoT Systems
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

High-precision detection of vehicle position and contour from unmanned aerial vehicles (UAV) provides critical information for vehicle behavior and traffic flow studies. Vehicles in UAV videos present unique features of small target pixels, which pose challenges in accurate detection. In addition, shaking of UAV camera, shadow of vehicle, and ground sign/marking also lead to difficulties in precise vehicle contour detection. The study proposes a novel approach that designs a bidirectional feedback framework (GKB) between optimized Gaussian mixture model and Kernel correlation filter to enhance vehicle detection. The framework predicts vehicle position based on information of continuous and correlated previous frames to achieve improved performance. We also improve the detection of closely spaced and dark vehicles with morphological algorithms and data processing. The approach is tested on two UAV videos with different shooting heights, illumination conditions, and traffic states. The results show that the proposed method significantly improves vehicle detection. The total accuracy of our model is 98%, which is a 11% improvement over the traditional single detect model and a 4% improvement over the track-after-detect method. Our model’s detection rate of closely spaced and dark vehicles is improved by 15–25% compared to previous methods. Our model’s vehicle contour detection accuracy is over 94%, which is about a 15% improvement over previous methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Data availability

The UAV video and vehicle trajectory data that support the findings of this study are available for access on the website http://www.seutraffic.com/#/download.

References

  1. Wang Z (2013) Visual traffic jam analysis based on trajectory data. IEEE Trans Visual Comput Graph 19(12):2159–2168

    Article  Google Scholar 

  2. Sopasakis A, Katsoulakis M (2016) Information metrics for improved traffic model fidelity through sensitivity analysis and data assimilation. Trans Res Part B: Methodol 86:1–18

    Article  Google Scholar 

  3. V-os J, Farah H, Hagenzieker M (2021) Speed behaviour upon approaching freeway curves. Accid Anal Prev 159:106276

    Article  Google Scholar 

  4. Monteil J et al (2014) Calibration, estimation, and sampling issues of car-following parameters. Trans Res Record: J Trans Res Board 2422:131–140

    Article  Google Scholar 

  5. Guo H, Wang Z, Yu B, Zhao H, Yuan X (2011) Tripvista: Triple perspective visual trajectory analytics and its application on microscopic traffic data at a road intersection. In Proc IEEE PacificVis 20:163–170

    Google Scholar 

  6. AT Palma, V Bogorny, B Kuijpers, LO Alvares (2008) A clusteringbased approach for discovering interesting places in trajectories. In: Proc ACM symposium on applied computing, p 863–868

  7. Lars Sommer, Nicole Schmidt, Arne Schumann1 Jurgen Beyerer (2018)Search area reduction fast-RCNN for fast vehicle detection in large aerial imagery. In: 2018 25th IEEE international conference on image processing (ICIP), p 3054–3058

  8. Qiwei Peng,Wang Luo, Gongyi Hong, Min Feng, Yuan Xia, Lei YuXiaolong Hao, Xu Wang, Mingxuan Li (2016) Pedestrian detection for transformer substation based on gaussian mixture model and YOLO.2016 In: 8th international conference on intelligent human-machine systems and cybernetics, p 562–565

  9. Razakarivony S, Jurie F (2016) Vehicle detection in aerial imagery: a small target detection benchmark. J Vis Commun Image Represent 34:187–203

    Article  Google Scholar 

  10. Krajewski R, Moers T, Eckstein L (2019) VeGAN: using GANs for augmentation in latent space to improve the semantic segmentation of vehicles in images from an aerial perspective. IEEE Winter Conf Appl Comput Vision (WACV) 2019:1440–1448

    Google Scholar 

  11. Mingqiang Chen, Qingling Zhao, Zhe Jiang, Rui Xu Intrusion. Detection for in-vehicle CAN networks based on auxiliary classifier GANs In: 2021 international conference on high performance big data and intelligent systems p.186–191.

  12. He K et al (2015) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904–1916

    Article  Google Scholar 

  13. Sang Jun, et al. (2017) Faster-RCNN model identification analysis. Journal of Chongqing University7

  14. Medera, Dusan, and S. Babinec. (2009) Incremental learning of convolutional neural networks.In: Ijcci 2009—Proceedings of the international joint conference on computational intelligence, Funchal, Madeira, Portugal, October DBLP, p 547–550

  15. Syed Tariq, Ali Kalpana Goyal. Moving object detection using self adaptive gaussian mixture model for real time applications. In: Proceeding international conference on recent innovations is signal processing and embedded systems (RISE-2017), p 27–29

  16. Bouwmans T (2009) Subspace learning for background modeling: a survey. Recent Patents Comput Sci 2(3):223–234

    Article  Google Scholar 

  17. Meng Liu, Chengdong Wu and Yunzhou Zhang (2007) Motion vehicle tracking based on multi-resolution optical flow and multi-scale harris corner detection In: Proceedings of the 2007 IEEE international conference on robotics and biomimetics, p 2032–2036

  18. Barnich O, Van Droogenbroeck M (2011) ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans Image Process 20(6):1709–1724

    Article  MathSciNet  MATH  Google Scholar 

  19. KaewTraKulPong, P., Bowden, R. (2002) An improved adaptive background mixture model for real-time tracking with shadow detection. In: P. Remagnino, G. Jones, N. Paragios, C. Regazzoni (eds.) Videobased surveillance systems, p.135–144

  20. Ke R et al (2019) Real-time traffic flow parameter estimation from UAV video based on ensemble classifier and optical flow. IEEE Trans Intell Transp Syst 20(1):54–64

    Article  Google Scholar 

  21. M. Kristan, R. Pflugfelder, A. Leonardis, J. Matas, F. Porikli, (2013) The Visual Object Tracking VOT2013 challenge results. In ICCV Workshops, p 98–111

  22. J.-Y. Lee and W. Yu. (2011) Visual tracking by partition-based histogram backprojection and maximum support criteria. In Proceedings of the IEEE international conference on robotics and biomimetic (ROBIO)

  23. Moeslund TB, Hilton A, Kruger V (2006) A survey of advances in vision-based human motion capture and analysis. Comp Vis Image Underst 2–3:90–126

    Article  Google Scholar 

  24. Ren W, Wang X, Member S, Tian J (2021) Tracking-by-counting: using network flows on crowd density maps for tracking multiple targets. IEEE Trans Image Process 30:1439–1452

    Article  MathSciNet  Google Scholar 

  25. Xinqiang Chen, Zhibin Li, Yongsheng Yang, Lei Qi, and Ruimin Ke (2019) High-resolution vehicle trajectory extraction and denoising from aerial videos. In: IEEE transactions

  26. Naima Amrouche ; Ali Khenchaf ; Daoud Berkani (2017) Multiple mode multi-target tracking in high noise environment using radar measurements. In: 2017 sensor signal processing for defence conference (SSPD).

  27. Z. Wang, H. Xiao, W. He, F. Wen and K. Yuan (2013) Real-Time SIFT-Based Object Recognition System, In: International conference on mechatronics and automation, Takamatsu

  28. Nimbalkar AK, Kahe RR, Patil CS (2014) Patil face and hand gesture recognition using principle component analysis and kNN classifier. Int J Comput Appl 8:26–28

    Google Scholar 

  29. Z. Zivkovic (2004) Improved adaptive gaussian mixture model for background subtraction. In: IEEE International Conference on Pattern Recognition, p 28–31

  30. C. Xie, M. Savvides, and B. Vijaya-Kumar (2005) Kernel correlation filter based redundant class-dependence feature analysis (KCFA) on FRGC2.0 data, In : analysis and modelling of faces and gestures

Download references

Author information

Authors and Affiliations

  1. Jinling Institute of Technology, 99 Hongjing Road, Nanjing, 211169, China

    Xiaofeng Shan & Chishe Wang

  2. Southeast University, 2 Si Pai Lou, Nanjing, 211169, China

    Qifan Wu & Zhibin Li

Authors
  1. Xiaofeng Shan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qifan Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhibin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chishe Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Qifan Wu or Zhibin Li.

Ethics declarations

Conflict of interest

The authors have no conflicts of interest to declare relevant to this article’s content.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shan, X., Wu, Q., Li, Z. et al. Bidirectional feedback of optimized gaussian mixture model and kernel correlation filter for enhancing simple detection of small pixel vehicles. Neural Comput & Applic 35, 8747–8761 (2023). https://doi.org/10.1007/s00521-022-07570-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07570-1

Keywords

Search

Navigation