Total views : 208

Maritime Vessels Real-time Tracking-by-detection in UAV Videos

Affiliations

  • Federal State Higher Military Educational Establishment, Nakhimov Black Sea Higher Naval School, Sevastopol, Russia

Abstract


Background/Objectives: This paper presents a fast real-time multi-object tracking algorithm adopted for maritime vessels tracking in UAV videos. Methods/Statistical Analysis: This research applies extended multi-object tracking-bydetection framework in highly dynamic UAV-captured maritime environment. Propagation is performed using particle filter whose particle weights are updated using modified observation model that incorporates a term based upon trackers affinity. The latter is also used for trackers grouping, that handles detector inaccuracies, and preventing identity switches by means of special propagation mode that is enabled when targets approach each other and start to overlap. Findings: Our research has shown that state-of-art multi-tracking algorithm is applicable to maritime vessels real-time tracking in UAV videos, provided the use of weak and fast online classifiers, which weakness is compensated by algorithm features based on trackers affinity matrix. Improvements/Applications: This paper presents an approach to maritime vessels tracking that allows to use fast, but less accurate, simple detectors and classifiers, enabling real-time processing on board of small-sized UAVs, while keeping decent precision and accuracy.

Keywords

Maritime Vessels Tracking, Multi-object Tracking, Particle Filter, Online Learning, Trackers Affinity, Trackingby- detection, UAV Surveillance.

Full Text:

 |  (PDF views: 133)

References


  • Ali S, Shad M. COCOA - Tracking in aerial imagery airborne intelligence surveillance reconnaissance ISR systems and applications III. SPIE; 2006:D2090.
  • Yu W, Yu X, Zhang P, Zhou J. A new framework of moving target detection and tracking for UAV video application.ISPRS08 Congress, Beijing, China, 2008 Jul 3–11; 2008.
  • Mattyus G, Benedek C, Sziranyi T. Multi target tracking on aerial video. ISPRS Instanbul Workshop 2010 on Modeling of optical airborne Sensors, WG I/4, IAPRS Vol. XXXVIII, part 1/W4, 2010 Oct 11–13; 2010.
  • Moreira RD, Ebecken NFF, Alves AS, Livernet F, CampilloNavetti A. A survey on video detection and tracking of maritime vessels. International Journal of Signal Processing.2016; 1:47–60.
  • Marques JS, Bernardino A, Cruz G, Bento M. An algorithm for the detection of vessels in aerial images. 2014 11th IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS), Seoul; 2014. p. 295–300. DOI: 10.1109/AVSS.2014.6918684.
  • Parameswaran S, Lane C, Bagnall B, Buck H. Marine object detection in UAV full-motion video. SPIE 9076, Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications XI, 907608; 2014. DOI: 10.1117/12.2049487.
  • Breitenstein MD, Reichlin F, Leibe B, Koller-Meier E, Van Gool L. Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2011; 33(9):1820–33.DOI: 10.1109/TPAMI.2010.232.
  • Grabner H, Leistner C, Bischof H. Semi-supervised on-line boosting for robust tracking. Computer Vision – ECCV.Volume 5302 of the series Lecture Notes in Computer Science; 2008. p. 234–47.
  • Choi W. Near-online multi-target tracking with aggregated local flow descriptor. ICCV; 2015.
  • Wang B, Wang G, Chan KL, Wang L. Tracklet association with online target-specific metric learning. IEEE Conference IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2015. p. 1234–241.
  • Leal-Taixé L, Milan A, Reid I, Roth S, Schindler K.MOTChallenge 2015: Towards a benchmark for multi-target tracking [Internet]. 2015 Apr. Available from: https:// arxiv.org/abs/1504.01942.
  • Wu Y, Lim J, Yang MH. Online object tracking: A benchmark.Conference on Computer Vision and Pattern Recognition Workshops; 2013. p. 2411–18.
  • Zhong W, Lu H, Yang M-H. Robust object tracking via sparsity-based collaborative model. IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2012.
  • Hare S, Saffari A, Torr PHS. Struck: structured output tracking with kernels. ICCV; 2011.
  • Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003; 25(5):564–77.
  • Sevilla-Lara L, Learned-Miller E. Distribution fields for tracking. IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2012.
  • Mei X, Ling H. Robust visual tracking using L1 minimization.ICCV; 2009.
  • Jia X, Lu H, Yang M-H. Visual tracking via adaptive structural local sparse appearance model. 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2012.
  • Kazantsev P, Skribtsov P, Surikov S. Fast multi-object tracking-by-detection using tracker affinity matrix. Indian Journal of Science and Technology. 2016 Jul; 9(27). DOI: 10.17485/ijst/2016/v9i27/97696.
  • Matas JO, Urban CM, Pajdla T. Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing. 2002; 22:384–93. DOI: 10.1016/j.imavis.2004.02.006.
  • Kazantsev P, Skribtsov P. Pedestrian detection in RGB-D data using deep autoencoders. American Journal of Applied Sciences. 2015; 12(11):847–56. DOI: 10.3844/ ajassp.2015.847.856.
  • Skribtsov P, Kazantsev P, Dolgopolov A. Head-shoulder detection using deep autoencoders Indian Journal of Science and Technology. 2016; 9(42):1–9.
  • Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images; 2009 .
  • Skribtsov P, Kazantsev P. Multi-layer neural network auto encoders learning method, using regularization for invariant image recognition. Indian Journal of Science and Technology. 2016; 9(27). DOI: 10.17485/ijst/2016/ v9i27/97704.
  • Bilmes JA. A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. Technical Report TR-97-021.International Computer Science Institute and Computer Science Division, University of California at Berkeley; 1998 Apr.
  • Cormen TH, Leiserson CE, Rivest RL, Stein C. Chapter 21: Data structures for Disjoint Sets. Introduction to Algorithms (Second ed.), MIT Press; 2001. p. 498–524.
  • Drones [Internet]. [Cited 2016 Dec 02]. Available from: http://www.dji.com/products.
  • Aerial drone videos by Photolab-gr [Internet]. [Cited 2016 Mar 01]. Available from: https://www.youtube.com/channel/ UC8OWcHE-SEthC4KQ7N82_Eg.
  • Bernardin K, Stiefelhagen R. Evaluating multiple object tracking performance: The Clear MOT Metrics. Journal of Image and Video Processing. 2008; (3):1–10.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.