Abstract
In this paper, we propose a level set tracking algorithm, which integrates the information of the original frame and the confidence predicted by the deep feature based detector. First, we extract features from convolutional neural network and select part of them to avoid redundancy. Secondly, the features are used to generate a confidence map of the tracked object through the detector. And then the confidence along with the original frame is applied in level set model to acquire the segmentation result. We introduce an outlier rejection scheme to further improve the result. Finally, updating is employed to the detector to adapt to the changes in the video. One important contribution of our work is to use the deep features in confidence prediction, particularly the usage of low-level features in the neural network. Experimental results show that our model delivers a better performance than the state-of-the-art on a series of challenging videos.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, X., Hu, W., Shen, C., Zhang, Z., Dick, A., Hengel, A.V.D.: A survey of appearance models in visual object tracking. ACM Trans. Intell. Syst. Technol. 4(4), 478–488 (2013)
Hu, W., Zhou, X., Li, W., Luo, W., Zhang, X., Maybank, S.: Active contour-based visual tracking by integrating colors, shapes and motions. IEEE Trans. Image Process. 22(5), 1778–1792 (2013)
Bibby, C., Reid, I.: Robust real-time visual tracking using pixel-wise posteriors. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5303, pp. 831–844. Springer, Heidelberg (2008). doi:10.1007/978-3-540-88688-4_61
Barbu, T.: Template matching based video tracking system using a novel n-step search algorithm and HOG features. In: International Conference on Neural Information Processing (ICONIP), Doha, pp. 328–336 (2012)
Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 4293–4302 (2016)
Zhang, K., Liu, Q., Wu, Y., Yang, M.H.: Robust visual tracking via convolutional networks without training. IEEE Trans. Image Process. 25(4), 1779–1792 (2016)
Hong, S., You, T., Kwak, S., Han, B.: Online tracking by learning discriminative saliency map with convolutional neural network. In: International Conference on Machine Learning, Lille, pp. 597–606 (2015)
Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, Santiago, pp. 3119–3127 (2015)
Ma, C., Huang, J., Yang, X., Yang, M.: Hierarchical convolutional features for visual tracking. In: IEEE Conference on Computer Vision, Santiago, pp. 3074–3082 (2015)
Yeh, Y., Hsu, C.: Online selection of tracking features using AdaBoost. IEEE Trans. Circ. Syst. Video Technol. 19(3), 442–446 (2009)
Godec, M., Roth, P.M., Bischof, H.: Hough-based tracking of non-rigid objects. In: IEEE International Conference on Computer Vision, Barcelona, vol. 117, no. 10, pp. 81–88 (2011)
Duffner, S., Garcia, C.: Fast pixelwise adaptive visual tracking of non-rigid objects. IEEE Trans. Image Process. 26(5), 2368–2380 (2017)
Duffner, S., Garcia, C.: PixelTrack: a fast adaptive algorithm for tracking non-rigid objects. In: IEEE International Conference on Computer Vision, Sydney, pp. 2480–2487 (2013)
Chan, T.F., Sandberg, B.Y., Vese, L.A.: Active contours without edges for vector-valued images. J. Vis. Commun. Image Represent. 11(2), 130–141 (2000)
Liu, L., Zhang, Q., Wu, M., Li, W., Shang, F.: Adaptive segmentation of magnetic resonance images with intensity inhomogeneity using level set method. Magn. Reson. Imaging 31(4), 567–574 (2013)
Sun, X., Yao, H., Zhang, S., Li, D.: Non-rigid object contour tracking via a novel supervised level set model. IEEE Trans. Image Process. 24(11), 3386–3399 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs.CV] (2014)
Collins, R.T., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1631–1643 (2005)
Avidan, S.: Ensemble tracking. IEEE Trans. Pattern Anal. Mach. Intell. 29(2), 261–271 (2007)
Tsai, D., Flagg, M., Rehg, J.M.: Motion coherent tracking with multi-label MRF optimization. Int. J. Comput. Vis. 100(2), 1–11 (2010)
Liu, L., Fan, S., Ning, X., Liao, L.: An efficient level set model with self-similarity for texture segmentation. Neurocomputing 266, 150–164 (2017)
Acknowledgments
This work is supported by National Natural Science Foundation of China under grant 61370133 and grant 61672095.
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
Ning, X., Liu, L. (2017). Level Set Based Online Visual Tracking via Convolutional Neural Network. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10636. Springer, Cham. https://doi.org/10.1007/978-3-319-70090-8_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-70090-8_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70089-2
Online ISBN: 978-3-319-70090-8
eBook Packages: Computer ScienceComputer Science (R0)