Improved CT algorithm based on target block division and feature points matching
Tóm tắt
For compressive tracking (CT) algorithm, it is vulnerable to the occlusion, when tracking targets. An improved CT algorithm based on target division and feature point matching is proposed in this paper, which can determine different target tracking states by the method of target division. When the target is in normal tracking or partial occlusion, the target is located accurately by the sub-block with the highest discrimination degree. In this scenario, the classifier only updates the unblocked sub regions in order to avoid the error of updating the occlusion information. When the target is completely occluded or lost in some frames, ORB feature matching is used to re-locate the target. Experimental results show that our proposed CT algorithm can improve the robustness of the algorithm and reduces the drift problem.
Tài liệu tham khảo
S Wang, H Lu, F Yang, et al., in Proceedings of the IEEE Conference on Computer Vision: November 6–13, 2011. Superpixel tracking (IEEE, Barcelona, 2014), pp. 1323–1330
A Bugeau, P Perez, Track and cut: simultaneous tracking and segmentation of multiple objects with graph cuts. EURASIP Journal on Image and Video Processing. 2, 447–454 (2008)
S Oron, A Bar-Hillel, D Levi, S Avidan, Locally orderless tracking. Int. J. Comput. Vis. 111, 213–228 (2015)
J Kwon, KM Lee, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition: June 20–25, 2009. Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo sampling (IEEE, Miami, FL, 2009), pp. 1208–1215
Z Kalal, J Matas, K Mikolajczyk, in Proceedings of the IEEE Conference on Computer Vision Workshops: Sept. 27 2009–Oct. 4 2009. On-line learning of robust object detectors during unstable tracking (IEEE, Kyoto, 2009), pp. 1417–1424
G Helmut, in Proceedings of the British Machine Vision Conference: September 4-7, 2006. Real-time tracking via on-line boosting (IEEE, Edinburgh, 2006), pp. 47–56
A Adam, E Rivlin, I Shimshoni, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition: June 17–22, 2006. Robust Fragments-based Tracking using the Integral Histogram (IEEE, New York, 2006), pp. 798–805
SMS Nejhum, J Ho, MH Yang, Visual tracking with histograms and articulating blocks. Computer Vision & Image Understanding 114, 901–914 (2008)
HX Li, CH Shen, QF Shi, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition: June 20–25,2011. Real-time visual tracking using compressive sensing (IEEE, Colorado Springs, 2011), pp. 1305–1312
K Zhang, L Zhang, MH Yang, in Proceedings of the European Conference on Computer Vision: October 7–13, 2012. Real-time compressive tracking (Springer, Florence, 2012), pp. 866–879
PM Fonseca, J Nesvadba, Face tracking in the compressed domain. EURASIP Journal on Advances in Signal Processing. 1, 1–11 (2006)
K Zhang, L Zhang, MH Yang, Fast compressive tracking. IEEE Trans. Pattern Anal. Mach. Intell. 36(10), 2002–2015 (2014)
QP Zhu, J Yan, DX Deng, Compressive tracking via oversaturated sub-region classifiers. IET Comput. Vis. 17(6), 448–455 (2013)
L ZHANG, J HAN, B LI, et al., The scale adaptive feature compressed tracking. J Natl Univ Defense Technol 35, 146–151 (2013)
PA Deotale, VJ Preetida, Object detection and localization using compressed sensing. Advances in Signal Processing and Intelligent Recognition Systems 678, 127–141 (2018)
DL Donoho, Compressed sensing. IEEE Trans. Inf. Theory 52, 1289–1306 (2006)
E Rosten, T Drummond, in Proceedings of the European Conference on Computer Vision: May 7–13, 2006. Machine learning for high-speed corner detection (Springer, Graz, 2006), pp. 430–443
MS Verkeenko, Development of an algorithm for fast corner points detection. Journal of Computer and Systems Sciences International 53(3), 392–401 (2014)
DG Lowe, Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91–110 (2004)
TTH Tran, E Marchand, in Proceedings of the IEEE Conference on Robotics and Automation: April 10–14, 2007. Real-time keypoints matching: application to visual servoing (IEEE, Roma, 2007), pp. 3787–3792
E Rublee, V Rabaud, K Konolige, et al., in Proceedings of the IEEE Conference on Computer Vision: Nov 6–13, 2011. ORB: an efficient alternative to SIFT or SURF (IEEE, Barcelona, 2012), pp. 2564–2571
W Huang, LD Wu, HC Song, et al., RBRIEF: a robust descriptor based on random binary comparisons. IET Computer Vision 7(1), 29–35 (2013)