Adaptive Framework for Multi-Feature Hybrid Object Tracking
Source abstract
Abstract
Object tracking is a computer vision task deemed necessary for high-level intelligent decision-making algorithms. Researchers have merged different object tracking techniques and discovered a new class of hybrid algorithms that is based on embedding a meanshift (MS) optimization procedure into the particle filter (PF) (MSPF) to replace its inaccurate and expensive particle validation processes. The algorithm employs a combination of predetermined features, implicitly assuming that the background will not change. However, the assumption of fully specifying the background of the object may not often hold, especially in an uncontrolled environment. The first innovation of this research paper is the development of a dynamically adaptive multi-feature framework for MSPF (AMF-MSPF) in which features are ranked by a ranking module and the top features are selected on-the-fly. As a consequence, it improves local discrimination of the object from its immediate surroundings. It is also highly desirable to reduce the already complex framework of the MSPF to save resources to implement a feature ranking module. Thus, the second innovation of this research paper introduces a novel technique for the MS optimization method, which reduces its traditional complexity by an order of magnitude. The proposed AMF-MSPF framework is tested on different video datasets that exhibit challenging constraints. Experimental results have shown robustness, tracking accuracy and computational efficiency against these constraints. Comparison with existing methods has shown significant improvements in term of root mean square error (RMSE), false alarm rate (FAR), and F-SCORE.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Infrared Target Detection Methodologies · Impact of Light on Environment and Health
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, University of Engineering and Technology, Taxila 47050, Pakistan
References (32)
Show source-provided references
1. Khattak, A.S., Raja, G., Anjum, N., and Qasim, M. (2014, January 17–19). Integration of Meanshift and Particle Filter: A Survey. Proceedings of the 2014 12th International Conference on Frontiers of Information Technology, Islamabad, Pakistan.10.1109/FIT.2014.60 ↗
2. Sahoo, P.K., Kanungo, P., and Parvathi, K. (2014, January 22–24). Three frame based adaptive background subtraction. Proceedings of the 2014 International Conference on High Performance Computing and Applications (ICHPCA), Bhubaneswar, India.10.1109/ICHPCA.2014.7045375 ↗
3. Probabilistic data association methods for tracking complex visual objects10.1109/34.927458 ↗
4. The estimation of the gradient of a density function, with applications in pattern recognition10.1109/TIT.1975.1055330 ↗
5. Comaniciu, D., Ramesh, V., and Meer, P. (2000, January 15). Real-time tracking of non-rigid objects using mean shift. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2000), Hilton Head Island, SC, USA.
6. Kernel-based object tracking10.1109/TPAMI.2003.1195991 ↗
7. Target tracking in airborne forward looking infrared imagery10.1016/S0262-8856(03)00059-3 ↗
8. Kernel-based object tracking using asymmetric kernels with adaptive scale and orientation selection10.1007/s00138-009-0237-4 ↗
9. Online selection of discriminative tracking features10.1109/TPAMI.2005.205 ↗
10. Fang, J., Yang, J., Liu, H., Lv, J., and Zhou, Y. (2010). Robust fragments-based tracking with adaptive feature selection. Opt. Eng., 49.10.1117/1.3481118 ↗
11. Mean shift through scale and occlusion10.1049/iet-spr.2011.0136 ↗
12. Gordon, N., Ristic, B., and Arulampalam, S. (2004). Beyond the Kalman Filter: Particle Filters for Tracking Applications, Artech House.
13. On sequential Monte Carlo sampling methods for Bayesian filtering10.1023/A:1008935410038 ↗
14. Novel approach to nonlinear/non-Gaussian Bayesian state estimation10.1049/ip-f-2.1993.0015 ↗
15. A particle filter for joint detection and tracking of color objects10.1016/j.imavis.2006.07.027 ↗
16. An adaptive color-based particle filter10.1016/S0262-8856(02)00129-4 ↗
17. Yang, C., Duraiswami, R., and Davis, L. (2005, January 17–21). Fast multiple object tracking via a hierarchical particle filter. Proceedings of the IEEE 2005 Computer Vision Conference, Beijing, China.
18. Isard, M., and MacCormick, J. (2001, January 7–14). BraMBLe: A Bayesian multiple-blob tracker. Proceedings of the 2001 Computer Vision European Conference, Vancouver, BC, Canada.
19. Patrick, P., Hue, C., Vermaak, J., and Gangnet, M. (2002). Color-based probabilistic tracking. Computer Vision on European Conference, Springer.
20. Robust visual tracking based on interactive multiple model particle filter by integrating multiple cues10.1016/j.neucom.2013.12.049 ↗
21. A tutorial on particle filters for online nonlinear/non-gaussian Bayesian tracking10.1109/78.978374 ↗
22. Kernel particle filter for visual tracking10.1109/LSP.2004.842254 ↗
23. Real-time hand tracking using a mean shift embedded particle filter10.1016/j.patcog.2006.12.012 ↗
24. A compact association of particle filtering and kernel based object tracking10.1016/j.patcog.2012.01.016 ↗
25. Chia, Y.S., Kow, W.Y., Khong, W.L., Kiring, A., and Teo, K.T.K. (2011, January 5–8). Kernel-based object tracking via particle filter and mean shift algorithm. Proceedings of the 2011 11th International Conference on Hybrid Intelligent Systems (HIS), Melacca, Malaysia.10.1109/HIS.2011.6122159 ↗
26. CamShift guided particle filter for visual tracking10.1016/j.patrec.2008.10.017 ↗
27. Maggio, E., and Cavallaro, A. (2005, January 23). Hybrid particle filter and mean shift tracker with adaptive transition model. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Philadelphia, PA, USA.
28. Visual tracking using an insect vision embedded particle filter10.1155/2015/573131 ↗
29. Multi-cue-based CamShift guided particle filter tracking10.1016/j.eswa.2010.11.111 ↗
30. A robust approach for multiple vehicles tracking using layered particle filter10.1016/j.aeue.2010.06.006 ↗
31. Normalized cuts and image segmentation10.1109/34.868688 ↗
32. Figureht sample degeneracy and impoverishment in particle filters: A review of intelligent approaches10.1016/j.eswa.2013.12.031 ↗