Aiming at the unstable performance on fast-moving and deformational target tracking in current kernel correlation filter (KCF), an innovative approach based on heterogeneous features fusion is proposed in this paper. Firstly, a histogram of oriented gradient is utilized to cater for motion state change in complex surveillance background. Combined with a colour-free template as a novel heterogeneous feature, the proposed approach improves the tracking performance on the fast-moving target in KCF. Subsequently, the optimized spatial regularization and quadruple block method are implemented in order to solve the difficulties of scale change and boundary effect in the cyclic matrix. The simulation results indicate that the proposed approach has better precision and success rate than other popular tracking algorithms when dealing with both fast motion and deformation on the platform of the object tracking benchmark and actual traffic datasets.
BolmeDSBeveridgeJRDraperBA, et al. (2010) Visual object tracking using adaptive correlation filters. In: IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, California, USA, 13–18 June 2010. Piscataway: Institute of Electrical and Electronics Engineers, 2544–2550.
2.
CaiYZYangDDMaoN, et al. (2017) Visual tracking algorithm based on adaptive convolutional features. Acta Optica Sinica37(3): 1–12.
3.
CaleroMJFAldásMLázaroJ, et al. (2019) Pedestrian detection under partial occlusion by using logic inference, HOG and SVM. IEEE Latin America Transactions17(9): 1552–1559.
4.
CorveeEBremondF (2010) Body parts detection for people tracking using trees of histogram of oriented gradient descriptors. In: IEEE International Conference on Advanced Video and Signal Based Surveillance, Boston, Massachusetts, USA, 29 August–1 September 2010. Piscataway: Institute of Electrical and Electronics Engineers, 469–475.
5.
DalalNTriggsB (2005) Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision & Pattern Recognition, San Diego, California, USA, 20–25 June 2005. Piscataway: Institute of Electrical and Electronics Engineers, 886-893.
6.
DanelljanMHägerGKhanFS, et al. (2014) Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference, Nottingham, UK, 1–5 September 2014, pp.1–11. Guildford: British Machine Vision Association Press. Available at: https://dx-doi-org.web.bisu.edu.cn/10.5244/C.28.65
7.
DanelljanMHägerGKhanFS, et al. (2017) Discriminative scale space tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence39(8): 1561–1575.
8.
HareSGolodetzSSaffariA, et al. (2016) Struck: Structured output tracking with kernels. IEEE Transactions on Pattern Analysis and Machine Intelligence38(10): 2096–2109.
9.
HenriquesJFCaseiroRMartinsP, et al. (2015) High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence37(3): 583–596.
10.
HuangDFLuoLChenZY, et al. (2017) Applying detection proposals to visual tracking for scale and aspect ratio adaptability. International Journal of Computer Vision122(3): 524–541.
11.
KalalZMikolajczykKMatasJ (2012) Tracking-learning-detection. IEEE Transactions on Pattern Analysis and Machine Intelligence34(7): 1409–1422.
12.
KeJMHongQCaiJY, et al. (2018) Long-term target tracking algorithm based on kernelized correlation filter with color-naming feature integration. Computer Systems & Applications27(4): 190–195.
13.
LiKXuWHanY, et al. (2020) Soft sensor for the moisture content of crude oil based on multi-kernel Gaussian process regression optimized by an adaptive variable population fruit fly optimization algorithm. Transactions of the Institute of Measurement and Control42(4): 770–785.
14.
LiuWZhaoWJLiC (2016) Long-term visual tracking based on spatio-temporal context. Acta Optica Sinica36(1): 1–8.
SuZYChangJDuB, et al. (2020) Real-time visual tracking using complementary kernel support correlation filters. Frontiers of Computer Science14(2): 417–429.
WangGQLiNZhangYG (2018) Hybrid consensus sigma point approximation nonlinear filter using statistical linearization. Transactions of the Institute of Measurement and Control40(8): 2517–2525.
19.
WangYCHuangHLiSM, et al. (2017) Adaptive target tracking algorithm based on fusion of two models. Application Research of Computers34(12): 3828–3833.
20.
WeiQ (2019) Research on object recognition method based on fusion of color and shape features. Masters Dissertation, Northeast Normal University, Changchun, People’s Republic of China. Available at: http://cdmd.cnki.com.cn/Article/CDMD-10200-1019841437.htm
21.
YanHXieMWangP, et al. (2019) Kernel-correlated filtering target tracking algorithm based on multi-features fusion. IEEE Access7: 96079–96084.
ZhangQY (2017) Design and implementation of tracking system based on DSST algorithm. Masters Dissertation, Huazhong University of Science & Technology, Wuhan, People’s republic of China. Available at: http://cdmd.cnki.com.cn/Article/CDMD-10487-1018803189.htm
24.
ZhangXGZhangYWangYJ (2010) Covariance tracking based on forgetting factor and Kalman filter. Acta Optica Sinica30(8): 2317–2323.
25.
ZhuKChenLHuX (2019) Rolling element bearing fault diagnosis based on multi-scale global fuzzy entropy, multiple class feature selection and support vector machine. Transactions of the Institute of Measurement and Control41(14): 4013–4022.
