Semi-supervised On-Line Boosting for Robust Tracking

  title={Semi-supervised On-Line Boosting for Robust Tracking},
  author={Helmut Grabner and Christian Leistner and Horst Bischof},
Recently, on-line adaptation of binary classifiers for tracking have been investigated. On-line learning allows for simple classifiers since only the current view of the object from its surrounding background needs to be discriminiated. However, on-line adaption faces one key problem: Each update of the tracker may introduce an error which, finally, can lead to tracking failure (drifting). The contribution of this paper is a novel on-line semi-supervised boosting method which significantly… 

On-line semi-supervised multiple-instance boosting

This work proposes an on-line semi-supervised learning algorithm which is able to combine both of these approaches into a coherent framework, which leads to more robust results than applying both approaches separately.

On-Line Multi-view Forests for Tracking

A novel on-line multi-view learning algorithm based on random forests that is fast, easy to implement, benefits from parallel computing architectures and inherently exploits multiple views for learning from unlabeled data.

Online Boosting-Based Object Tracking

A novel and robust framework for automatic visual object tracking from image sequences or video is presented to incorporate decision of given by a prior learned strong detector and an on-line adaptation tracking mechanism to solve the drifting and losing of tracking object during tracking.

Robust Object Tracking using Semi-Supervised Online Boosting

Experiments show that this new object tracking method using semi-supervised on-line boosting is very robust to misaligned object model updates and moreover performs on a similar performance level as other equivalent state-of-the-art object tracking methods.

PROST: Parallel robust online simple tracking

This work shows that augmenting an on-line learning method with complementary tracking approaches can lead to more stable results, and uses a simple template model as a non-adaptive and thus stable component, a novel optical-flow-based mean-shift tracker as highly adaptive element and anon-line random forest as moderately adaptive appearance-based learner.

Improved semi-supervised online boosting for object tracking

An improved online semi-supervised boosting method, in which the learning process is guided by positive (P) and negative (N) constraints, termed P-N constraints, which restrict the labeling of the unlabeled samples, which can effectively improve the discriminative ability of the classifier and significantly alleviate the drifting problem in tracking applications.

Robust Object Tracking with Online Multiple Instance Learning

It is shown that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks.

Robust visual tracking via online semi-supervised co-boosting

A novel visual tracking algorithm via online semi-supervised co-boosting, which has a good ability to recover from drifting by incorporating prior knowledge of the object while being adaptive to appearance changes by effectively combining the complementary strengths of different feature views.

Real-Time Object Tracking Via Online Discriminative Feature Selection

It is shown that integrating prior information of instance labels and the most correct positive instance into a supervised learning algorithm can handle visual drift more effectively and efficiently than the existing MIL tracker.


A fast visual tracking algorithm is proposed to make the tracker more accurate and stable in the complex variations situations like occlusions, illuminations and shape deformations and an optimization process is used to reduce the computational burden.



Learning Features for Tracking

Contrary to existing approaches, this paper is able to start tracking of the object from scratch requiring no off-line training phase before tracking and can be used for real-time applications since on-line updating and evaluating classifiers can be done efficiently.

Real-Time Tracking via On-line Boosting

A novel on-line AdaBoost feature selection algorithm for tracking that allows to adapt the classifier while tracking the object and selects the most features for tracking resulting in stable tracking results.

On-line Boosting and Vision

  • H. GrabnerH. Bischof
  • Computer Science
    2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
This paper proposes a novel on-line AdaBoost feature selection method and demonstrates the multifariousness of the method on such diverse tasks as learning complex background models, visual tracking and object detection.

Co-Tracking Using Semi-Supervised Support Vector Machines

This paper treats tracking as a foreground/background classification problem and proposes an online semi- supervised learning framework that improves each individual classifier using the information from other features, thus leading to a more robust tracker.

Ensemble Tracking

  • S. Avidan
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2007
This work considers tracking as a binary classification problem, where an ensemble of weak classifiers is trained online to distinguish between the object and the background, and combines them into a strong classifier using AdaBoost.

Incremental Learning for Visual Tracking

This paper presents an efficient and effective online algorithm that incrementally learns and adapts a low dimensional eigenspace representation to reflect appearance changes of the target, thereby facilitating the tracking task.

Semi-supervised boosting using visual similarity learning

A novel semi-supervised learning method which combines the power of learned similarity functions and classifiers, formulated in a boosting framework, which improves a state-of-the-art detector by using labeled and unlabeled data.

Online selection of discriminative tracking features

  • R. CollinsYanxi Liu
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2005
This paper presents an online feature selection mechanism for evaluating multiple features while tracking and adjusting the set of features used to improve tracking performance, and notes susceptibility of the variance ratio feature selection method to distraction by spatially correlated background clutter.

Tracking Using Online Feature Selection and a Local Generative Model

An algorithm for online feature selection which improves robustness to occlusions by referring to a localized generative appearance model which exhibits the properties of non-negativity, localization and orthogonality is proposed.

Rapid object detection using a boosted cascade of simple features

  • Paul A. ViolaMichael J. Jones
  • Computer Science
    Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.