Abstract
Compared with the traditional visual tracking, online vehicle tracking in aerial imagery brings lots of unique challenges including low frame rate sampling, small tracked targets, to name a few. As we know, color information provides rich information of the tracked objects especially when the texture features of small objects are not easily observed. Thus, in this work, we attempt to combine different color models within the correlation-filter-based tracking framework for tracking vehicles in aerial images. First, we exploit a set of color models to describe the appearance of the tracked object based on correlation filters. Second, the confidence maps generated by these correlation filters are selected based on the variance rule and combined using an adaptive fusion method. Finally, we conduct numerous experiments on the KIT_IPF aerial dataset to compare the proposed tracker with other competing methods and analyze the effects of different components. The experimental results not only demonstrate that our tracker performs better than other state-of-the-art algorithms but also show that the adopted feature selection and fusion schemes could facilitate improving the tracking performance.
Z. Liu and Z. Wang—Contributed equally to this work.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The target appearance model \(\bar{x}\) is learned over time.
References
Babenko, B., Yang, M., Belongie, S.J.: Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. 33(8), 1619–1632 (2011)
Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: CVPR, pp. 2544–2550 (2010)
Candemir, S., Palaniappan, K., Bunyak, F., Seetharaman, G.: Feature fusion using ranking for object tracking in aerial imagery. Geosp. Infofus. II 8396, 839604-1–839604-9 (2012)
Collins, R.T., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1631–1643 (2005)
Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: ICCV, pp. 4310–4318 (2015)
Danelljan, M., Khan, F.S., Felsberg, M., van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR, pp. 1090–1097 (2014)
Everts, I., van Gemert, J.C., Gevers, T.: Evaluation of color STIPs for human action recognition. In: CVPR, pp. 2850–2857 (2013)
Hare, S., Golodetz, S., Saffari, A., Vineet, V., Cheng, M., Hicks, S.L., Torr, P.H.S.: Struck: structured output tracking with kernels. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2096–2109 (2016)
Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 702–715. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33765-9_50
Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)
Liang, P., Blasch, E., Ling, H.: Encoding color information for visual tracking: algorithms and benchmark. IEEE Trans. Image Process. 24(12), 5630–5644 (2015)
Ma, C., Huang, J., Yang, X., Yang, M.: Hierarchical convolutional features for visual tracking. In: ICCV, pp. 3074–3082 (2015)
Mei, X., Ling, H.: Robust visual tracking and vehicle classification via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 33(11), 2259–2272 (2011)
Palaniappan, K., Bunyak, F., Kumar, P., Ersoy, I., Jäger, S., Ganguli, K., Haridas, A., Fraser, J., Rao, R.M., Seetharaman, G.: Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video. In: FUSION, pp. 1–8 (2010)
Ross, D.A., Lim, J., Lin, R., Yang, M.: Incremental learning for robust visual tracking. Int. J. Comput. Vis. 77(1–3), 125–141 (2008)
Wang, D., Lu, H., Chen, Y.: Object tracking by multi-cues spatial pyramid matching. In: ICIP, pp. 3957–3960 (2010)
Wang, D., Lu, H., Yang, M.: Online object tracking with sparse prototypes. IEEE Trans. Image Process. 22(1), 314–325 (2013)
Wu, Y., Lim, J., Yang, M.: Online object tracking: a benchmark. In: CVPR, pp. 2411–2418 (2013)
Yang, F., Lu, H., Chen, Y.-W.: Human tracking by multiple kernel boosting with locality affinity constraints. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6495, pp. 39–50. Springer, Heidelberg (2011). doi:10.1007/978-3-642-19282-1_4
Zhang, K., Zhang, L., Yang, M.: Fast compressive tracking. IEEE Trans. Pattern Anal. Mach. Intell. 36(10), 2002–2015 (2014)
Zhong, W., Lu, H., Yang, M.: Robust object tracking via sparse collaborative appearance model. IEEE Trans. Image Process. 23(5), 2356–2368 (2014)
Acknowledgements
This work was supported by the Undergraduate Innovation and Entrepreneurship Training Program (No. 2017101410201010981) and Fundamental Research Funds for the Central Universities (No. DUT16RC(4)16).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Liu, Z., Wang, Z., Lu, H., Wang, D. (2017). Online Vehicle Tracking in Aerial Imagery. In: Sun, Y., Lu, H., Zhang, L., Yang, J., Huang, H. (eds) Intelligence Science and Big Data Engineering. IScIDE 2017. Lecture Notes in Computer Science(), vol 10559. Springer, Cham. https://doi.org/10.1007/978-3-319-67777-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-67777-4_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67776-7
Online ISBN: 978-3-319-67777-4
eBook Packages: Computer ScienceComputer Science (R0)