A Probabilistic Approach to Integrating Multiple Cues in Visual Tracking

Du, Wei; Piater, Justus

doi:10.1007/978-3-540-88688-4_17

Cited by 35 publications

(29 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the proposed local-motion model can help resolve ambiguities associated with multiple visually similar targets, it can be used in existing probabilistic multi-cue integration frameworks like [32,8,16], or as extension to multipletarget tracking schemes, such as [31], to increase their robustness when tracking visually-similar targets. Note also that the local-motion-based feature is general enough to be used not only within the framework of particle filters, but also with non-stochastic methods: For example, the discrimination-based trackers such as the recently proposed AdaBoost tracker [33] or the level-set-based blob trackers like [34,35].…”

Section: Resultsmentioning

confidence: 99%

“…A drawback of methods which rely on image differencing is that they are essentially local-change detectors and therefore cannot resolve situations when a target is occluded by a moving, visually similar, object. Du et al [16] have proposed a general multiple-cue integration framework based on Linked Hidden Markov Models and integrated the detected local-changes with other visual features to improve tracking when the tracked object does not exhibit any motion.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A local-motion-based probabilistic model for visual tracking

Kristan

Perš

Kovačič

et al. 2009

Pattern Recognition

View full text Add to dashboard Cite

Color-based tracking is prone to failure in situations where visually similar targets are moving in a close proximity or occlude each other. To deal with the ambiguities in the visual information, we propose an additional color-independent visual model based on the target's local motion. This model is calculated from the optical flow induced by the target in consecutive images. By modifying a color-based particle filter to account for the target's local motion, the combined color/local-motion-based tracker is constructed. We compare the combined tracker to a purely color-based tracker on a challenging dataset from hand tracking, surveillance and sports. The experiments show that the proposed local-motion model largely resolves situations when the target is occluded by, or moves in front of, a visually similar object.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A local-motion-based probabilistic model for visual tracking

Kristan

Perš

Kovačič

et al. 2009

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…The chance of finding discriminative features is clearly increased when combining multiple cues. Numerous papers on multi-cue tracking have demonstrated the concept of different cues complementing each other and overcoming the failure cases of individual cues [6,9,24,31,48,55]. A typical example is a hand being tracked while it moves in front of the face.…”

Section: Visual Tracking Of a Single Objectmentioning

confidence: 99%

A Vision-Based Remote Control

Stenger

Woodley

Cipolla

2010

Studies in Computational Intelligence

View full text Add to dashboard Cite

This chapter presents a vision-based system for touch-free interaction with a display at a distance. A single camera is fixed on top of the screen and is pointing towards the user. An attention mechanism allows the user to start the interaction and control a screen pointer by moving their hand in a fist pose directed at the camera. On-screen items can be chosen by a selection mechanism. Current sample applications include browsing video collections as well as viewing a gallery of 3D objects, which the user can rotate with their hand motion. We have included an up-to-date review of hand tracking methods, and comment on the merits and shortcomings of previous approaches. The proposed tracker uses multiple cues, appearance, color, and motion, for robustness. As the space of possible observation models is generally too large for exhaustive online search, we select models that are suitable for the particular tracking task at hand. During a training stage, various off-the-shelf trackers are evaluated. From this data different methods of fusing them online are investigated, including parallel and cascaded tracker evaluation. For the case of fist tracking, combining a small number of observers in a cascade results in an efficient algorithm that is used in our gesture interface. The system has been on public display at conferences where over a hundred users have engaged with it.

show abstract

“…There are some methods that have achieved a fast object tracking and detection, such as improving character description (i.e. like integral image [11]), and using a better classifier (i.e. the classifier should balance the performance and the efficiency).…”

Section: Introductionmentioning

confidence: 99%

Real-Time Visual Tracking Based on an Appearance Model and a Motion Mode

Zhang

2013

Intelligent Computing Theories and Technology

View full text Add to dashboard Cite

Abstract. Object tracking is a challenging problem in computer vision community. It is very difficult to solve it efficiently due to the appearance or motion changes of the object, such as pose, occlusion, or illumination. Existing online tracking algorithms often update models with samples from observations in recent frames. And some successful tracking algorithms use more complex models to make the performance better. But most of them take a long time to detect the object. In this paper, we proposed an effective and efficient tracking algorithm with an appearance model based on features extracted from the multiscale image feature space with data-independent basis and a motion mode based on Gaussian perturbation. In addition, the features used in our approach are compressed in a small vector, making the classifier more efficient. The motion model based on random Gaussian distribution makes the performance more effective. The proposed algorithm runs in real-time and performs very well against some existing algorithms on challenging sequences.

show abstract

A Probabilistic Approach to Integrating Multiple Cues in Visual Tracking

Cited by 35 publications

References 22 publications

A local-motion-based probabilistic model for visual tracking

A local-motion-based probabilistic model for visual tracking

A Vision-Based Remote Control

Real-Time Visual Tracking Based on an Appearance Model and a Motion Mode

Contact Info

Product

Resources

About