Face tracking with a probabilistic Viola and Jones face detector

Sanabria-Macias, Frank; Marrón, M.; Macías-Guarasa, Javier; Pizarro, Daniel; Turnes, Javier Noa; Reyes, Enrique Juan Marañón

doi:10.1109/iecon.2019.8927133

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, instead of adding all pose outputs, like in [ 2 , 23 ], we select the best pose (

) as that with the highest response value (described in Equation ( 17 )), proven to reduce the number of false positives in preliminary experiments.

…”

Section: Video Observation Modelmentioning

confidence: 99%

See 1 more Smart Citation

Audiovisual Tracking of Multiple Speakers in Smart Spaces

Sanabria-Macias,

Marron-Romera,

Macias-Guarasa

2023

Sensors

Self Cite

View full text Add to dashboard Cite

This paper presents GAVT, a highly accurate audiovisual 3D tracking system based on particle filters and a probabilistic framework, employing a single camera and a microphone array. Our first contribution is a complex visual appearance model that accurately locates the speaker’s mouth. It transforms a Viola & Jones face detector classifier kernel into a likelihood estimator, leveraging knowledge from multiple classifiers trained for different face poses. Additionally, we propose a mechanism to handle occlusions based on the new likelihood’s dispersion. The audio localization proposal utilizes a probabilistic steered response power, representing cross-correlation functions as Gaussian mixture models. Moreover, to prevent tracker interference, we introduce a novel mechanism for associating Gaussians with speakers. The evaluation is carried out using the AV16.3 and CAV3D databases for Single- and Multiple-Object Tracking tasks (SOT and MOT, respectively). GAVT significantly improves the localization performance over audio-only and video-only modalities, with up to 50.3% average relative improvement in 3D when compared with the video-only modality. When compared to the state of the art, our audiovisual system achieves up to 69.7% average relative improvement for the SOT and MOT tasks in the AV16.3 dataset (2D comparison), and up to 18.1% average relative improvement in the MOT task for the CAV3D dataset (3D comparison).

show abstract

“…Next, instead of adding all pose outputs, like in [ 2 , 23 ], we select the best pose (

) as that with the highest response value (described in Equation ( 17 )), proven to reduce the number of false positives in preliminary experiments.

…”

Section: Video Observation Modelmentioning

confidence: 99%

“…Many of the approaches proposed in the literature for people localization within a monitored scene use information from a single type of sensor (video cameras [ 1 , 2 , 3 ], microphone arrays [ 4 , 5 , 6 ], infrared beacons [ 7 , 8 , 9 ], and others). Among them, the most used ones are video cameras and microphone arrays.…”

Section: Introductionmentioning

confidence: 99%