Model-Based Image Sequence Coding

Buck, Matthias; Diehl, Norbert

doi:10.1007/978-1-4615-3236-1_10

Cited by 13 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The means of finding new guesses, compensating motion, and finding an appropriate means of calculating error evolved over the next decades. The work was pioneered by Forchheimer and Kronander (1989), Aizawa and Harashima (Choi et al, 1994;Aizawa et al, 1989), Buck (1993), Diehl (1991), and Pandizic (Pandizic et al, 2003). Although the problem is far from answered, this research made it well realized.…”

Section: Parameterized Facial Analysismentioning

confidence: 99%

Facial Feature Tracking via Evolutionary Multiobjective Optimization

Larson

Yen

2010

International Journal of Applied Evolutionary Computation

View full text Add to dashboard Cite

Facial feature tracking for model–based coding has evolved over the past decades. Of particular interest is its application in very low bit rate coding in which optimization is used to analyze head and shoulder sequences. We present the results of a computational experiment in which we apply a combination of non-dominated sorting genetic algorithm and a deterministic search to find optimal facial animation parameters at many bandwidths simultaneously. As objective functions are concerned, peak signal-to-noise ratio is maximized while the total number of facial animation parameters is minimized. Particularly, the algorithm is tested for efficiency and reliability. The results show that the overall methodology works effectively, but that a better error assessment function is needed for future study.

show abstract

Section: Parameterized Facial Analysismentioning

confidence: 99%

Facial Feature Tracking via Evolutionary Multiobjective Optimization

Larson

Yen

2010

International Journal of Applied Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…The introduction of object-based coding techniques has led to widespread use of head models, as the human head is one of the most common objects to be found in scenes of restricted content [2,7,44]. In particular, video-conferencing and distance learning are two of the most popular applications requiring the use of model-based techniques, due to their inherent suitability and the need for low bit-rate coding solutions.…”

Section: Introductionmentioning

confidence: 99%