Hierarchical Convolution Feature for Target Tracking with Kernel-Correlation Filtering
Abstract
Target tracking is widely used in many fields, but tracking performance still needs to be improved due to factors such as deformation, illumination and occlusion. In this paper, we propose a scale adaptive target tracking solution based on hierarchical convolution features and establish a kernel correlation filtering target tracking framework that combines multi-layer convolution features. The improved convolutional neural network is used to extract multi-layer features, and the correlation filters of each layer are separately trained to perform weighted fusion to obtain the target position. Then, the edge box algorithm is adopted to obtain the size of the actual tracking frame to achieve exact target tracking. An extensive evaluation on OTB-2013 with public test sequences are conducted. Experimental results and analysis indicate that our method is better than other known advanced tracking algorithms even in video sequences with many uncertain factors, while the speed and accuracy of tracking can be effectively improved.
Keywords
Object tracking Convolution neural network Kernel correlation filter Edge boxesReferences
- 1.Chang, C., Ansari, R.: Kernel particle filter for visual tracking. IEEE Signal Process. Lett. 12(3), 242–245 (2005)CrossRefGoogle Scholar
- 2.Torkaman, B., Farrokhi, M.: Real-time visual tracking of a moving object using pan and tilt platform: A Kalman filter approach. In: 20th Iranian Conference on Electrical Engineering, Iran, pp. 56–67 (2012)Google Scholar
- 3.Hare, S., Saffari, A., Torr, P.H.S.: Struck: structured output tracking with kernels. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2096–2109 (2015)CrossRefGoogle Scholar
- 4.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_62CrossRefGoogle Scholar
- 5.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). https://doi.org/10.1007/978-3-642-33765-9_50CrossRefGoogle Scholar
- 6.Henriques, J.F., Caseiro, R., Martins, P., et al.: High-Speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)CrossRefGoogle Scholar
- 7.Ma, C., Huang, J.B., Yang, X., et al.: Hierarchical convolutional features for visual tracking. In: IEEE International Conference on Computer Vision 2015, pp 111–121. IEEE, Chile (2015)Google Scholar
- 8.Cui, Z., Xiao, S., Feng, J., et al.: Recurrently target-attending tracking. In: IEEE Conference on Computer Vision and Pattern Recognition 2016, pp. 1449–1458. IEEE, LAS VEGAS (2016)Google Scholar
- 9.Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Science, pp. 569–577 (2014)Google Scholar
- 10.Schölkopf, B., Smola, A.: Learning with kernels: support vector machines, regularization, optimization, and beyond. Am. Stat. Assoc. 98(462), 489 (2002)Google Scholar
- 11.Dollár, P., Zitnick, C.L.: Structured forests for fast edge detection. In: IEEE International Conference on Computer Vision 2013, pp. 854–863. IEEE, Sydney (2013)Google Scholar