Visual Object Tracking: The Initialisation Problem

Model initialisation is an important component of object tracking. Tracking algorithms are generally provided with the first frame of a sequence and a bounding box (BB) indicating the location of the object. This BB may contain a large number of background pixels in addition to the object and can lead to parts-based tracking algorithms initialising their object models in background regions of the BB. In this paper, we tackle this as a missing labels problem, marking pixels sufficiently away from the BB as belonging to the background and learning the labels of the unknown pixels. Three techniques, One-Class SVM (OC-SVM), Sampled-Based Background Model (SBBM) (a novel background model based on pixel samples), and Learning Based Digital Matting (LBDM), are adapted to the problem. These are evaluated with leave-one-video-out cross-validation on the VOT2016 tracking benchmark. Our evaluation shows both OC-SVMs and SBBM are capable of providing a good level of segmentation accuracy but are too parameter-dependent to be used in real-world scenarios. We show that LBDM achieves significantly increased performance with parameters selected by cross validation and we show that it is robust to parameter variation.

[1]  Ales Leonardis,et al.  Robust Visual Tracking Using an Adaptive Coupled-Layer Visual Model , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Vibhav Vineet,et al.  Struck: Structured Output Tracking with Kernels , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Aykut Erdem,et al.  Deformable part-based tracking by coupled global and local correlation filters , 2016, J. Vis. Commun. Image Represent..

[4]  Ales Leonardis,et al.  Robust visual tracking using template anchors , 2016, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

[5]  Bohyung Han,et al.  Learning Multi-domain Convolutional Neural Networks for Visual Tracking , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Yi Wu,et al.  Online Object Tracking: A Benchmark , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Zhenyu He,et al.  The Visual Object Tracking VOT2016 Challenge Results , 2016, ECCV Workshops.

[9]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[10]  Chandan Srivastava,et al.  Support Vector Data Description , 2011 .

[11]  Ales Leonardis,et al.  Single target tracking using adaptive clustered decision trees and dynamic multi-level appearance models , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Yuanjie Zheng,et al.  Learning based digital matting , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[13]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Jin Young Choi,et al.  Visual tracking of non-rigid objects with partial occlusion through elastic structure of local patches and hierarchical diffusion , 2015, Image Vis. Comput..

[15]  David Salesin,et al.  A Bayesian approach to digital matting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[16]  Qi Tian,et al.  Geometric Hypergraph Learning for Visual Tracking , 2016, IEEE Transactions on Cybernetics.

[17]  Marc Van Droogenbroeck,et al.  ViBe: A Universal Background Subtraction Algorithm for Video Sequences , 2011, IEEE Transactions on Image Processing.

[18]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[19]  Jiri Matas,et al.  Pixel-Wise Object Segmentations for the VOT 2016 Dataset , 2017 .

[20]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

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

[22]  Kyoung Mu Lee,et al.  Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo sampling , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.