A decoupled approach to exemplar-based unsupervised learning
Proceedings of the 25th international conference on Machine learning
Online selection of tracking features using AdaBoost
IEEE Transactions on Circuits and Systems for Video Technology
Adaptive pyramid mean shift for global real-time visual tracking
Image and Vision Computing
Tracking people in video sequences using multiple models
Multimedia Tools and Applications
Generalised relaxed Radon transform (GR2T) for robust inference
Pattern Recognition
Discriminative bayesian active shape models
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Target Tracking Using Multiple Patches and Weighted Vector Median Filters
Journal of Mathematical Imaging and Vision
A survey of appearance models in visual object tracking
ACM Transactions on Intelligent Systems and Technology (TIST) - Survey papers, special sections on the semantic adaptive social web, intelligent systems for health informatics, regular papers
Robust Bayesian fitting of 3D morphable model
Proceedings of the 10th European Conference on Visual Media Production
Hi-index | 0.01 |
Tracking objects in video using the mean shift (MS) technique has been the subject of considerable attention. In this work, we aim to remedy one of its shortcomings. MS, like other gradient ascent optimization methods, is designed to find local modes. In many situations, however, we seek the global mode of a density function. The standard MS tracker assumes that the initialization point falls within the basin of attraction of the desired mode. When tracking objects in video this assumption may not hold, particularly when the target's displacement between successive frames is large. In this case, the local and global modes do not correspond and the tracker is likely to fail. A novel multibandwidth MS procedure is proposed which converges to the global mode of the density function, regardless of the initialization point. We term the procedure annealed MS, as it shares similarities with the annealed importance sampling procedure. The bandwidth of the procedure plays the same role as the temperature in conventional annealing. We observe that an over-smoothed density function with a sufficiently large bandwidth is unimodal. Using a continuation principle, the influence of the global peak in the density function is introduced gradually. In this way, the global maximum is more reliably located. Since it is imperative that the computational complexity is minimal for real-time applications, such as visual tracking, we also propose an accelerated version of the algorithm. This significantly decreases the number of iterations required to achieve convergence. We show on various data sets that the proposed algorithm offers considerable promise in reliably and rapidly finding the true object location when initialized from a distant point