Abstract
We propose a novel salient superpixel based tracking algorithm using Coarse-to-Fine segmentation on graph model, where target state is estimated by a combination of pixel-level cues and middle-level cues to achieve accurate target appearance model. We exploit temporal optical flow and color distribution characteristics as coarse grained information from pixel-level processing, and propagate to fine-grained superpixels to improve initial target appearance segmentation from bounding box annotations. Our algorithm constructs a graph model with manifold ranking by improved superpixels to estimate the saliency of target foreground and background in subsequent frames. The tracking result is located by calculating the weight of multi-scale box, where the weight depends on the similarity of scores of foreground and background superpixels in the scale box. We compared our algorithm with the existing techniques in OTB100 dataset, and achieved substantially better performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yang, C., Zhang, L.: Saliency detection via graph-based manifold ranking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3166–3173. IEEE, Portland (2013)
Achanta, R.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)
Belagiannis, V., Schubert, F., Navab, N., Ilic, S.: Segmentation based particle filtering for real-time 2D object tracking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 842–855. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33765-9_60
Rother, C., Kolmogorov, V.: Grabcut: interactive foreground extraction using iterated graph cuts. In: ACM SIGGRAPH, Los Angeles, vol. 23, pp. 309–314 (2004)
Liu, Q.: Decontaminate feature for tracking: adaptive tracking via evolutionary feature subset. J. Electron. Imaging 26(6), 1 (2017)
Son, J., Jung, I.: Tracking-by-segmentation with online gradient boosting decision tree. In: International Conference on Computer Vision (ICCV), pp. 3056–3064. IEEE, Santiago (2015)
Ren, X., Malik, J.: Tracking as repeated figure/ground segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–8. IEEE, Hawaii (2007)
Yan, Y., Ren, J.: Cognitive fusion of thermal and visible imagery for effective detection and tracking of pedestrians in videos. Cognit. Comput. 10(1), 94–104 (2018)
Kalal, Z., Mikolajczyk, K.: Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1409–1422 (2012)
Xu, C.: Robust visual tracking via online multiple instance learning with Fisher information. Pattern Recognit. 48(12), 3917–3926 (2015)
Hare, S., Saffari, A., Torr, P.H.S.: Struck: structured output tracking with kernels. In: 13th International Conference on Computer Vision (ICCV), pp. 263–270. IEEE, Barcelona (2011)
Wang, S., Lu, H.: Superpixel tracking. In: 13th International Conference on Computer Vision (ICCV), pp. 1323–1330. IEEE, Barcelona (2011)
Yang, F.: Robust superpixel tracking. IEEE Trans. Image Process. 23(4), 1639–1651 (2014)
Zhou, X.: Learning a superpixel-driven speed function for level set tracking. IEEE Trans. Cybern. 46(7), 1498–1510 (2016)
Hong, Z., Wang, C., Mei, X., Prokhorov, D., Tao, D.: Tracking using multilevel quantizations. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 155–171. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_11
Xiao, J., Stolkin, R., Leonardis, A.: Single target tracking using adaptive clustered decision trees and dynamic multilevel appearance models. In: Computer Vision and Pattern Recognition (CVPR), pp. 4978–4987. IEEE, Boston (2015)
Yeo, D., Son, J., Han, B., Han, J.H.: Superpixel-based tracking-by-segmentation using Markov chains. In: Computer Vision and Pattern Recognition (CVPR), pp. 511–520. IEEE, Hawaii (2017)
Wang, L., Lu, H., Yang, M.H.: Constrained superpixel tracking. IEEE Trans. Cybern. 48(3), 1030–1041 (2018)
Liu, C.: Beyond pixels: exploring new representations and applications for motion analysis. Doctoral Thesis. Massachusetts Institute of Technology (2009)
Lucchi, A., Li, Y., Smith, K., Fua, P.: Structured image segmentation using kernelized features. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, pp. 400–413. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33709-3_29
Rosenfeld, A., Weinshall, D.: Extracting foreground masks towards object recognition. In: IEEE International Conference on Computer Vision (ICCV), 1371–1378. IEEE (2011)
Chai, Y., Ren, J., Zhao, H., et al.: Hierarchical and multi-featured fusion for effective gait recognition under variable scenarios. Pattern Anal. Appl. 19(4), 905–917 (2016)
Ezrinda, M.Z., Kamarul Hawari, G., Ren, J., Mohd Zuki, S.: A hybrid thermal-visible fusion for outdoor human detection. J. Telecommun. Electron. Comput. Eng. (JTEC) 10(1–4), 79–83 (2018)
Yan, Y., et al.: Unsupervised image saliency detection with Gestalt-laws guided optimization and visual attention based refinement. Pattern Recognit. 79, 65–78 (2018)
Wang, Z., et al.: A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos. Neurocomputing 287, 68–83 (2018)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Wu, Y.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 37(9), 1834–1848 (2015)
Zhang, K., Zhang, L., Yang, M.-H.: Real-time compressive tracking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 864–877. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33712-3_62
Babenko, B., Yang, M.-H.: Visual tracking with online multiple instance learning. In: Computer Vision and Pattern Recognition (CVPR), pp. 983–990. IEEE, Florida (2009)
Liu, B., Huang, J.: Robust tracking using local sparse appearance model and k-selection. In: Computer Vision and Pattern Recognition (CVPR), pp. 1313–1320. IEEE (2011)
Acknowledgment
This research is supported by National Natural Science Foundation of China (61772144, 61672008), Innovation Research Project of Education Department of Guangdong Province (Natural Science) (2016KTSCX077), Foreign Science and Technology Cooperation Plan Project of Guangzhou Science Technology and Innovation Commission (201807010059), Guangdong Provincial Application-oriented Technical Research and Development Special Fund Project (2016B010127006), the Natural Science Foundation of Guangdong Province (2016A030311013), and the Scientific and Technological Projects of Guangdong Province (2017A050501039). The corresponding author is Huimin Zhao.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhan, J., Zhao, H. (2018). Salient Superpixel Visual Tracking with Coarse-to-Fine Segmentation and Manifold Ranking. In: Ren, J., et al. Advances in Brain Inspired Cognitive Systems. BICS 2018. Lecture Notes in Computer Science(), vol 10989. Springer, Cham. https://doi.org/10.1007/978-3-030-00563-4_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-00563-4_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00562-7
Online ISBN: 978-3-030-00563-4
eBook Packages: Computer ScienceComputer Science (R0)