A precise approach to tracking dim-small targets using spectral fingerprint features

Abstract

A precise method for accurately tracking dimsmall targets, based on spectral fingerprint is proposed where traditional full color tracking seems impossible. A fingerprint model is presented to adequately extract spectral features. By creating a multidimensional feature space and extending the limited RGB information to the hyperspectral information, the improved precise tracking model based on a nonparametric kernel density estimator is built using the probability histogram of spectral features. A layered particle filter algorithm for spectral tracking is presented to avoid the object jumping abruptly. Finally, experiments are conducted that show that the tracking algorithm with spectral fingerprint features is accurate, fast, and robust. It meets the needs of dim-small target tracking adequately.

Keywords

dim-small target / precise tracking / spectral fingerprint features / LPF algorithm for spectral tracking

References

[1] Doucet A, Gordon N, Krishnamurthy V. Particle filters for state estimation of jump Markov linear systems. IEEE Transactions on Signal Processing, 2001, 49(3): 613-624

[2] Gao J, Kosaka A, Kak A. A multi-Kalman filtering approach for video tracking of human-delineated objects in cluttered environments. Computer Vision and Image Understanding, 2005, 99(1): 1-57

[3] Meyer M, Ohmacht T, Bosch R, Hotter M. Video surveillance applications using multiple views of a scene. IEEE Aerospace and Electronic Systems Magazine, 1999, 14(3): 13-18

[4] Wang L, Hu S, Zhang X. Detecting and tracking of small moving target under the background of sea level. In: Proceedings of the 9th International Conference on Signal Processing. 2008, 989-992

[5] Hamdulla A, Xiang G, Tursun D. A particle filter and fuzzy clustering based algorithm for tracking dim moving multiple point targets in ir image sequence. In: Proceedings of 2009 WRI World Congress on Computer Science and Information Engineering. 2009, 205-209

[6] Chen J, An G, Zhang S, Wu Z. Small target tracking based on histogram interpolation mean shift. Journal of Electronics and Information Technology, 2010, 32(9): 2119-2125

[7] Neumann J. DMD based hyperspectral augmentation for multi-object tracking systems. In: Proceedings of Emerging Digital Micromirror Device Based Systems and Applications, SPIE-7210. 2009, 110-119

[8] Varsano L, Rotman S. Point target tracking in hyperspectral images. In: Proceedings of Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XI, SPIE-5806. 2005, 503-512

[9] Varsano L, Yatskaer I, Rotman S. Temporal target tracking in hyperspectral images. Optical Engineering, 2006, 45(12): 126201

[10] Aminov B, Nichtern O, Rotman S. Spatial and temporal point tracking in real hyperspectral images. EURASIP Journal on Advances in Signal Processing, 2011, 2011(1): 1-25

[11] Rosario D, Kling H. Hyperspectral object tracking using small sample size. In: Hyperspectral, and Ultraspectral Imagery XVI, SPIE-7695. 2010, 230-238

[12] Banerjee A, Burlina P, Broadwater J. Hyperspectral video for illumination-invariant tracking. In: Proceedings of the 1st Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. 2009, 1-4

[13] Kerekes J, Baum J. Hyperspectral imaging system modeling. Lincoln Laboratory Journal, 2003, 14(1): 117-130

[14] Wang T, Zhu Z, Blasch E. Bio-inspired adaptive hyperspectral imaging for real-time target tracking. IEEE Sensors Journal, 2010, 10(3): 647-654

[15] Nguyen H V, Banerjee A, Chellappa R. Tracking via object reflectance using a hyperspectral video camera. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2010, 44-51

[16] Garcia-Allende P, Conde O, Mirapeix J, Cobo A, Lopez-Higuera J. Quality control of industrial processes by combining a hyperspectral sensor and Fisher’s linear discriminant analysis. Sensors and Actuators B: Chemical, 2008, 129(2): 977-984

[17] Wettle M, Daniel P, Logan G, Thankappan M. Assessing the effect of hydrocarbon oil type and thickness on a remote sensing signal: a sensitivity study based on the optical properties of two different oil types and the hymap and quickbird sensors. Remote Sensing of Environment, 2009, 113(9): 2000-2010

[18] Delabrouille J, Cardoso J, Patanchon G. Multi-detector multicomponent spectral matching and applications for cmb data analysis. Monthly Notices of the Royal Astronomical Society. 2002, 1-16

[19] Blackburn J, Mendenhall M, Rice A, Shelnutt P, Soliman N, Vasquez J. Feature aided tracking with hyperspectral imagery. In: Proceedings of Signal and Data Processing of Small Targets, SPIE-6699. 2007, 1-12

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg