Multiple Reliable Structured Patches for Object Tracking

It is essential to build the effective appearance model for object tracking in computer vision. Most object trackers can be roughly divided into two categories according to the appearance model: the bounding box model and the patch model. The bounding box model cannot handle shape deformation and occlusion of the non-rigid moving object effectively. The patch model is prone to be disturbed by complex backgrounds. In this paper, we propose a robust multi-structured-patch appearance model to represent the target for object tracking. The proposed appearance model is aimed to exploit and identify reliable patches that can be tracked effectively through the whole tracking process. According to attention mechanism in biological vision system, a coarse-to-fine strategy is usually used to search the target. Therefore, the proposed appearance model is represented by robust patches in different sizes, in which the bigger patches search the rough region of the target and the smaller patches estimate the accurate location. Experimental results on OTB100 dataset show that the proposed method outperforms state-of-the-art trackers.

[1]  Huchuan Lu,et al.  GradNet: Gradient-Guided Network for Visual Object Tracking , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[2]  Wei Chen,et al.  Visual tracking based on robust appearance model , 2019, Image Vis. Comput..

[3]  Pengfei Wang,et al.  Kernel correlation filters for visual tracking with adaptive fusion of heterogeneous cues , 2018, Neurocomputing.

[4]  Li Zhang,et al.  Exploiting the Anisotropy of Correlation Filter Learning for Visual Tracking , 2019, International Journal of Computer Vision.

[5]  Zhaohui Hao,et al.  Correlation filter-based visual tracking via adaptive weighted CNN features fusion , 2018, IET Image Process..

[6]  Qiang Wang,et al.  Visual Tracking via Spatially Aligned Correlation Filters Network , 2018, ECCV.

[7]  Simone Calderara,et al.  Visual Tracking: An Experimental Survey , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Huchuan Lu,et al.  Visual tracking via adaptive structural local sparse appearance model , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Rui Caseiro,et al.  High-Speed Tracking with Kernelized Correlation Filters , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Geun-Sik Jo,et al.  Robust visual tracking based on global-and-local search with confidence reliability estimation , 2019, Neurocomputing.

[11]  Jin Gao,et al.  Transfer Learning Based Visual Tracking with Gaussian Processes Regression , 2014, ECCV.

[12]  Wei Li,et al.  Visual tracking with tree-structured appearance model for online learning , 2019, IET Image Process..

[13]  Cordelia Schmid,et al.  DeepMatching: Hierarchical Deformable Dense Matching , 2015, International Journal of Computer Vision.

[14]  Huchuan Lu,et al.  Visual Tracking via Adaptive Spatially-Regularized Correlation Filters , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Michael Felsberg,et al.  Accurate Scale Estimation for Robust Visual Tracking , 2014, BMVC.

[16]  Yang Li,et al.  YES NO Cartesian Update Update Feature Extraction Feature Extraction Phase Correlation Resample Min Eq . 3 ? Fourier spaceLog-Polar Cross Correlation Model Fourier space Model Sample Sample , 2018 .

[17]  Junseok Kwon,et al.  Deep Meta Learning for Real-Time Target-Aware Visual Tracking , 2017, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[18]  Zhongfei Zhang,et al.  A survey of appearance models in visual object tracking , 2013, ACM Trans. Intell. Syst. Technol..

[19]  Keqin Li,et al.  Visual tracking via context-aware local sparse appearance model , 2018, J. Vis. Commun. Image Represent..

[20]  Xiaolin Zhang,et al.  Robust Scale Adaptive and Real-Time Visual Tracking with Correlation Filters , 2016, IEICE Trans. Inf. Syst..

[21]  Seunghoon Hong,et al.  Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network , 2015, ICML.

[22]  Stan Sclaroff,et al.  MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization , 2014, ECCV.

[23]  Gérard G. Medioni,et al.  Context tracker: Exploring supporters and distracters in unconstrained environments , 2011, CVPR 2011.

[24]  Xing Hu,et al.  An Anti-occlusion and Scale Adaptive Kernel Correlation Filter for Visual Object Tracking , 2019, KSII Trans. Internet Inf. Syst..

[25]  Yan Wei,et al.  Accurate Scale Adaptive and Real-Time Visual Tracking with Correlation Filters , 2018, IEICE Trans. Inf. Syst..

[26]  Nadjiba Terki,et al.  Hierarchical convolutional features for visual tracking via two combined color spaces with SVM classifier , 2018, Signal, Image and Video Processing.

[27]  Sang Min Yoon,et al.  Visual Object Tracking Using Structured Sparse PCA-Based Appearance Representation and Online Learning , 2018, Sensors.

[28]  Luc Van Gool,et al.  Learning Discriminative Model Prediction for Tracking , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[29]  Honggang Zhang,et al.  Deep Attentive Tracking via Reciprocative Learning , 2018, NeurIPS.

[30]  Liang Lin,et al.  Visual Tracking via Dynamic Graph Learning , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.