Long-term multiobject tracking using alternative correlation filters

We propose a real-time multiobject-tracking approach that is minimally affected by environmental conditionsand target appearance change. The aim of the proposed approach is to track any object in a scene, regardless of objecttype, since tracking all of the objects in a scene is critical and widely used in surveillance applications. Thus, motiondetection results are used to initialize the trackers. The proposed object-tracking approach is realized with two typesof independent correlation filters estimating location and scale. Alternative correlation filters representing differentappearances of the target are also proposed in order to increase the robustness of the approach to scene and targetchanges. Tracking sustainability is provided by putting alternative correlation filters into use when the quality of thetracking output decreases to a critical level. Motion blobs are also used to minimize object boundary drift, whichis a challenging problem, especially for long-term tracking. The proposed approach was tested on an object-trackingbenchmark dataset and outperformed most state-of-the-art methods.

PDF

___

McCall JC, Trivedi MM. Video-based lane estimation and tracking for driver assistance: survey, system and evaluation. IEEE Trans Intell Transp Syst 2006; 7: 20-37.
Santiago CB, Sousa A, Estriga ML, Reis LP, Lames M. Survey on team tracking techniques applied to sports. In: AIS 2010 International Conference on Autonomous and Intelligent Systems; 21–23 June 2010; Povoa de Varzim, Portugal. pp. 1-6.
Smeulders AW, Chu DM, Cucchiara R, Calderara S, Dehghan A, Shah M. Visual tracking: an experimental survey. IEEE T Pattern Anal 2014; 36: 1442-1468.
Baker S, Matthews I. Lucas-kanade 20 years on: a unifying framework. Int J Comput Vis 2004; 56: 221-255.
Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean-shift. In: IEEE 2000 Conference on Computer Vision and Pattern Recognition; 13–15 June 2000; Hilton Head Island, SC, USA. New York, NY, USA: IEEE. pp. 142-149.
Godec M, Roth PM, Bischof H. Hough-based tracking of non-rigid objects. Comput Vis Image Underst 2013; 117: 1245-1256.
Hare S, Golodetz S, Saffari A, Vineet V, Cheng M, Hicks SL, Torr PH. Struck: Structured output tracking with kernels. IEEE T Pattern Anal 2016; 38: 2096-2109.
Kalal Z, Matas J, Mikolajczyk K. Pn learning: Bootstrapping binary classifiers by structural constraints. In: IEEE 2010 Conference on Computer Vision and Pattern Recognition; 13–18 June 2010; San Francisco, CA, USA. New York, NY, USA: IEEE. pp. 49-56.
Bolme DS, Beveridge JR, Draper BA, Lui YM. Visual object tracking using adaptive correlation filters. In: IEEE 2010 Conference on Computer Vision and Pattern Recognition; 13–18 June 2010; San Francisco, CA, USA. New York, NY, USA: IEEE. pp. 2544-2550.
Danelljan M, Hager G, Khan F, Felsberg M. Accurate scale estimation for robust visual tracking. In: BMVA 2014 British Machine Vision Conference; 1–5 September 2014; Nottingham, UK. Durham, UK: BMVA Press.
Li Y, Zhu J. Background segmentation with feedback: A scale adaptive kernel correlation filter tracker with feature integration. In: Springer 2014 European Conference on Computer Vision; 6–12 September 2014; Zurich, Switzerland. Berlin, Germany: Springer. pp. 254-265.
Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: IEEE 2005 Conference on Computer Vision and Pattern Recognition; 20–25 June 2005; San Diego, CA, USA. New York, NY, USA: IEEE. pp. 886-893.
Vojir T, Noskova J, Matas J. Robust scale-adaptive mean-shift for tracking. Pattern Recognit Lett 2014; 49: 250-258.
Hong Z, Chen Z, Wang C, Mei X, Prokhorov D, Tao D. Multi-store tracker (muster): A cognitive psychology inspired approach to object tracking. In: IEEE 2015 Conference on Computer Vision and Pattern Recognition; 7–12 June 2015; Boston, MA, USA. New York, NY, USA: IEEE. pp. 749-758.
Danelljan M, Robinson A, Khan F, Felsberg M. Beyond correlation filters: Learning continuous convolution operators for visual tracking. In: IEEE 2016 European Conference on Computer Vision; 8–16 October 2016; Amsterdam, the Netherlands. New York, NY, USA: IEEE. pp. 472-488.
Nam H, Han B. Learning multi-domain convolutional neural networks for visual tracking. In: IEEE 2016 Conference on Computer Vision and Pattern Recognition Workshops; 26 June–1 July 2016; Las Vegas, NV, USA. New York, NY, USA: IEEE. pp. 4293-4302
Danelljan M, Hager G, Khan F, Felsberg M. Learning spatially regularized correlation filters for visual tracking. In: IEEE 2015 International Conference on Computer Vision; 11–18 December 2015; Santiago, Chile. New York, NY, USA: IEEE. pp. 4310-4318.
Hoffman M, Tiefenbacher P, Rigoll G. Background segmentation with feedback: The pixel-based adaptive segmenter. In: IEEE 2012 Computer Society Conference on Computer Vision and Pattern Recognition Workshops; 16–21 June 2012; Rhode Island, USA. New York, NY, USA: IEEE. pp. 38-43.
Kristan M, Matas J, Leonardis A, Felsberg M, Cehovin L, Fernandez G, Vojir T, Hager G, Nebehay G, Pflugfelder R. The visual object tracking vot2015 challenge results. In: IEEE 2015 International Conference on Computer Vision Workshops; 11–18 December 2015; Santiago, Chile. New York, NY, USA: IEEE. pp. 564-586.
Wu Y, Lim J, Yang MH. Object tracking benchmark. IEEE T Pattern Anal 2015; 37: 1834-1848.