Accurate 3D Tracking of Rigid Objects with Occlusion Using Active Appearance Models

Mittrapiyanuruk, Pradit; DeSouza, Guilherme N.; Kak, Avinash C.

doi:10.1109/acvmot.2005.15

Cited by 18 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, some methods report good results, without giving actual numbers on accuracy, such as [1,14,21,22]. Approaches described by [21,23,34,35] are capable of handling partial occlusion or changing lighting conditions but cannot differentiate between deteriorating tracking conditions and lost tracks. Some methods are restricted in their degrees of freedom, e.g.…”

Section: Related Workmentioning

confidence: 99%

Advances in real-time object tracking

Mörwald

Prankl

Zillich

et al. 2013

J Real-Time Image Proc

View full text Add to dashboard Cite

The huge amount of literature on real-time object tracking continuously reports good results with respect to accuracy and robustness. However, when it comes to the applicability of these approaches to real-world problems, often no clear statements about the tracking situation can be made. This paper addresses this issue and relies on three novel extensions to Monte Carlo particle filtering. The first, confidence dependent variation, together with the second, iterative particle filtering, leads to faster convergence and a more accurate pose estimation. The third, fixed particle poses removes jitter and ensures convergence. These extensions significantly increase robustness and accuracy, and further provide a basis for an algorithm we found to be essential for tracking systems performing in the real world: tracking state detection. Relying on the extensions above, it reports qualitative states of tracking as follows. Convergence indicates if the pose has already been found. Quality gives a statement about the confidence of the currently tracked pose. Loss detects when the algorithm fails. Occlusion determines the degree of occlusion if only parts of the object are visible. Building on tracking state detection, a model completeness scheme is proposed as a measure of which views of the object have already been learned and which areas require further inspection. To the best of our knowledge, this is the first tracking system that explicitly addresses the issue of estimating the tracking state. Our open-source framework is available online, serving as an easy-access interface for usage in practice.

show abstract

Section: Related Workmentioning

confidence: 99%

Advances in real-time object tracking

Mörwald

Prankl

Zillich

et al. 2013

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…Online estimation is essentially a stochastic optimization problem, since only noisy objective function evaluations are available due to restrictions on the sample set size at each instance. There are a number of advantages of online/stochastic learning over batch learning 4 . For example, it has been widely reported that it can reduce training time [21], has the ability to escape from shallow local minima [22], minimizes the true risk rather than the empirical risk [23], requires far less memory, and it does not require the number of samples to be chosen a priori.…”

Section: Stochastic Gradient Descentmentioning

confidence: 99%

“…where n b is the mini-batch size, stochastic optimization then proceeds by first 4 Batch learning minimizes the empirical risk over the whole training set simultaneously.…”

Section: Stochastic Gradient Descentmentioning

confidence: 99%

See 1 more Smart Citation

Learning AAM fitting through simulation

Saragih

Göcke

2009

Pattern Recognition

View full text Add to dashboard Cite

“…Since its advent by Edwards et al in [6] and their preliminary extension [5], the method has found applications in many image modelling, alignment and tracking problems, for example [7,8,11].…”

Section: Introductionmentioning

confidence: 99%