Adaptive linear predictors for real-time tracking

Hölzer, Stefan M.; Ilić, Slobodan; Navab, Nassir

doi:10.1109/cvpr.2010.5539851

Cited by 11 publications

(29 citation statements)

References 19 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[12] demonstrated that Linear Predictors are superior to Jacobian approximation and Holzer et al . [2] showed an experiment where Linear Predictors are superior to Efficient Second-order Minimization (ESM) [11]. We further fortify the latter by showing additional comparisons in Sec.…”

Section: Related Workmentioning

confidence: 99%

“…Most of them are based on energy minimization [3][4][5][6][7][8][9][10][11] and in many cases, an analytical derivation of the Jacobian is used in order to provide real-time tracking capabilities. Alternative approaches are based on learning [1,[12][13][14][15][16][17]2] where the relation between image intensity differences and template warping parameters is learned. While energy minimization is flexible at runtime, learning based methods have proven to allow much faster tracking.…”

Section: Introductionmentioning

confidence: 99%

“…This especially holds for applications running on lowend hardware such as mobile devices. Previous approaches either had to learn Linear Predictors offline [1], or start with a small template and iteratively grow it over time [2]. We propose a fast and simple learning procedure which reduces the necessary training time by up to two orders of magnitude while also slightly improving the tracking robustness with respect to large motions and image noise.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Efficient Learning of Linear Predictors Using Dimensionality Reduction

Hölzer

Ilić

Tan

et al. 2013

Computer Vision – ACCV 2012

Self Cite

View full text Add to dashboard Cite

Abstract. Using Linear Predictors for template tracking enables fast and reliable real-time processing. However, not being able to learn new templates online limits their use in applications where the scene is not known a priori and multiple templates have to be added online, such as SLAM or SfM. This especially holds for applications running on lowend hardware such as mobile devices. Previous approaches either had to learn Linear Predictors offline [1], or start with a small template and iteratively grow it over time [2]. We propose a fast and simple learning procedure which reduces the necessary training time by up to two orders of magnitude while also slightly improving the tracking robustness with respect to large motions and image noise. This is illustrated in an exhaustive evaluation where we compare our approach with state-of-the-art approaches. Additionally, we show the learning and tracking in mobile phone applications which demonstrates the efficiency of the proposed approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Efficient Learning of Linear Predictors Using Dimensionality Reduction

Hölzer

Ilić

Tan

et al. 2013

Computer Vision – ACCV 2012

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although, faster convergence rates for larger convergence areas can be additionally obtained by using a high-order instead of a first-order approximation of the error function, it is difficult in finding an appropriate nonlinear model to regress the predictor in different magnitudes of displacements and different template size. [8] has showed an experiment where linear predictors are superior to [6]. Moreover, an inappropriate high-order model is more sensitive to noise than linear model.…”

Section: Mixture Hyperplanes Approximationmentioning

confidence: 99%

Mixture Hyperplanes Approximation for Global Tracking

Xie

2015

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARY Template tracking has been extensively studied in Computer Vision with a wide range of applications. A general framework is to construct a parametric model to predict movement and to track the target. The difference in intensity between the pixels belonging to the current region and the pixels of the selected target allows a straightforward prediction of the region position in the current image. Traditional methods track the object based on the assumption that the relationship between the intensity difference and the region position is linear or non-linear. They will result in bad tracking performance when just one model is adopted. This paper proposes a method, called as Mixture Hyperplanes Approximation, which is based on finite mixture of generalized linear regression models to perform robust tracking. Moreover, a fast learning strategy is discussed, which improves the robustness against noise. Experiments demonstrate the performance and stability of Mixture Hyperplanes Approximation.

show abstract

“…Recently (Holzer et al, 2010) used adaptive linear predictors for real-time tracking. Adaptation is done by growth or reduction of the tracked patch during tracking and update of the regression matrices.…”

Section: Related Workmentioning

confidence: 99%

Fast Learnable Object Tracking and Detection in High-Resolution Omnidirectional Images

Hurych¹,

Zimmermann²,

Svoboda

2011

Proceedings of the International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:This paper addresses object detection and tracking in high-resolution omnidirectional images. The foreseen application is a visual subsystem of a rescue robot equipped with an omnidirectional camera, which demands real time efficiency and robustness against changing viewpoint. Object detectors typically do not guarantee specific frame rate. The detection time may vastly depend on a scene complexity and image resolution. The adapted tracker can often help to overcome the situation, where the appearance of the object is far from the training set. On the other hand, once a tracker is lost, it almost never finds the object again. We propose a combined solution where a very efficient tracker (based on sequential linear predictors) incrementally accommodates varying appearance and speeds up the whole process. We experimentally show that the performance of the combined algorithm, measured by a ratio between false positives and false negatives, outperforms both individual algorithms. The tracker allows to run the expensive detector only sparsely enabling the combined solution to run in real-time on 12 MPx images from a high resolution omnidirectional camera (Ladybug3).

show abstract

Adaptive linear predictors for real-time tracking

Cited by 11 publications

References 19 publications

Efficient Learning of Linear Predictors Using Dimensionality Reduction

Efficient Learning of Linear Predictors Using Dimensionality Reduction

Mixture Hyperplanes Approximation for Global Tracking

Fast Learnable Object Tracking and Detection in High-Resolution Omnidirectional Images

Contact Info

Product

Resources

About