A joint particle filter for audio-visual speaker tracking

Nickel, Kai; Gehrig, Tobias; Stiefelhagen, Rainer; McDonough, John

doi:10.1145/1088463.1088477

Cited by 78 publications

(39 citation statements)

References 24 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most proposed systems for this type of application rely on continuous tracking of identified people in the room. Important approaches that are previously proposed and successfully used are Kalman filters [25] and particle filters [34]. However, tracking multiple people for a long period is difficult, there is little possibility of recovering from mistakes.…”

Section: Feature Based Identification Modulementioning

confidence: 99%

“…They were previously employed for audio-visual multi-person tracking [20,55], multimodal event detection [54] and for active speaker tracking [14,34] successfully. In [55] the PF model incorporates the 3D location and velocity of tracked objects, and also employed for calibrating the sensors.…”

Section: Particle Filter-based Trackingmentioning

confidence: 99%

“…In [55] the PF model incorporates the 3D location and velocity of tracked objects, and also employed for calibrating the sensors. In [34] the PF model is used for 3D locations only, and the motion of the object is modeled with a Gaussian diffusion equation. In [14], the 2D ground position of the person and the height are tracked for a multiple person activity tracking system.…”

Section: Particle Filter-based Trackingmentioning

confidence: 99%

See 2 more Smart Citations

Multimodal identification and localization of users in a smart environment

Salah

Morros

Luque

et al. 2008

J Multimodal User Interfaces

View full text Add to dashboard Cite

Detecting the location and identity of users is a first step in creating contextaware applications for technologically-endowed environments. We propose a system that makes use of motion detection, person tracking, face identification, feature-based identification, audio-based localization, and audio-based identification modules, fusing information with particle filters to obtain robust localization and identification. The data streams are processed with the help of the generic client-server middleware SmartFlow, resulting in a flexible architecture that runs across different platforms.

show abstract

Section: Feature Based Identification Modulementioning

confidence: 99%

Section: Particle Filter-based Trackingmentioning

confidence: 99%

Section: Particle Filter-based Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal identification and localization of users in a smart environment

Salah

Morros

Luque

et al. 2008

J Multimodal User Interfaces

View full text Add to dashboard Cite

show abstract

“…In particular, over the last few years, the particle filter framework is reported to be effective for tracking people [1,2,3,4,5,6,7,8,9,10,12,13]. The particle filter is a Bayesian sequential importance sampling technique, which recursively approximates the posterior distribution using a finite set of weighted samples.…”

Section: Introductionmentioning

confidence: 99%

3D Head Tracking using the Particle Filter with Cascaded Classifiers

Kobayashi¹,

Sugimura²,

Sato³

et al. 2006

Procedings of the British Machine Vision Conference 2006

View full text Add to dashboard Cite

We propose a method for real-time people tracking using multiple cameras. The particle filter framework is known to be effective for tracking people, but most of existing methods adopt only simple perceptual cues such as color histogram or contour similarity for hypothesis evaluation. To improve the robustness and accuracy of tracking more sophisticated hypothesis evaluation is indispensable. We therefore present a novel technique for human head tracking using cascaded classifiers based on AdaBoost and Haar-like features for hypothesis evaluation. In addition, we use multiple classifiers, each of which is trained respectively to detect one direction of a human head. During real-time tracking the most suitable classifier is adaptively selected by considering each hypothesis and known camera position. Our experimental results demonstrate the effectiveness and robustness of our method.

show abstract

“…In [8,9] particle filters are applied to track persons in 3D using a top-down approach. Each particle is evaluated for all available cameras by using cascaded classifiers as proposed by Viola and Jones [10].…”

Section: Related Workmentioning

confidence: 99%

3D Person Tracking with a Color-Based Particle Filter

Wildermann

Teich

Robot Vision

View full text Add to dashboard Cite

Abstract. Person tracking is a key requirement for modern service robots. But methods for robot vision have to fulfill several constraints: they have to be robust to errors evoked by noisy sensor data, they have to be able to work under realworld conditions, and they have to be fast and computationally inexpensive. In this paper we present an approach for tracking the position of a person in 3D based on a particle filter. In our framework, each particle represents a hypothesis for the 3D position, velocity and size of the person's head being tracked. Two cameras are used for the evaluation of the particles. The particles are weighted by projecting them onto the camera image and applying a color-based perception model. This model uses skin color cues for face tracking and color histograms for body tracking. In contrast to feature-based approaches, our system even works when the person is temporary or partially occluded.

show abstract

A joint particle filter for audio-visual speaker tracking

Cited by 78 publications

References 24 publications

Multimodal identification and localization of users in a smart environment

Multimodal identification and localization of users in a smart environment

3D Head Tracking using the Particle Filter with Cascaded Classifiers

3D Person Tracking with a Color-Based Particle Filter

Contact Info

Product

Resources

About