3-D motion estimation of human head for model-based image coding

Fukuhara, T.; Murakami, Takahiro

doi:10.1049/ip-i-2.1993.0006

Cited by 9 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Skita [6] and Suenaga [15] used centroid points of the head and face area to calculate the orientation of the head. A neural network method was proposed by Fukuhara [9], who used a three-layer model and a training set comprising 397 possible motion patterns.…”

Section: The Feature Point Extractormentioning

confidence: 99%

A three-dimensional muscle-based facial expression synthesizer for model-based image coding

Lei

Ouhyoung

1996

Signal Processing: Image Communication

View full text Add to dashboard Cite

Section: The Feature Point Extractormentioning

confidence: 99%

A three-dimensional muscle-based facial expression synthesizer for model-based image coding

Lei

Ouhyoung

1996

Signal Processing: Image Communication

View full text Add to dashboard Cite

“…M ANY applications in human-computer interface, threedimensional (3-D) video games, model-based video coding [2], [3], talking agents [4], and distance learning demand rendering of realistic human faces [5]- [7]. In recent years, computer speed boosted by dramatic hardware improvement has made real-time rendering of face models possible.…”

Section: Introductionmentioning

confidence: 99%

Compression of MPEG-4 facial animation parameters for transmission of talking heads

Tao

Chen

et al. 1999

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

The emerging MPEG-4 standard supports the transmission and composition of facial animation with natural video. The new standard will include a facial animation parameter (FAP) set that is defined based on the study of minimal facial actions and is closely related to muscle actions. The FAP set enables model-based representation of natural or synthetic talking-head sequences and allows intelligible visual reproduction of facial expressions, emotions, and speech pronunciations at the receiver. This paper addresses the data-compression issue of talking heads and presents three methods for bit-rate reduction of FAP's. Compression efficiency is achieved by way of transform coding, principal component analysis, and FAP interpolation. These methods are independent of each other in nature and thus can be applied in combination to lower the bit-rate demand of FAP's, making possible the transmission of multiple talking heads over band-limited channels. The basic methods described here have been adopted into the MPEG-4 Visual Committee Draft [1] and are readily applicable to other articulation data such as body animation parameters. The efficacy of the methods is demonstrated by both subjective and objective results.

show abstract

“…The first problem is also known as head tracking and can be solved with traditional techniques for 3D motion estimation e.g., [2,3]. To this end, both matching and gradient-based techniques [4][5][6] could be used.…”

Section: Introductionmentioning

confidence: 99%