Idioma:

Real-Time 3D Head Pose Tracking Through 2.5D Constrained Local Models with Local Neural Fields

Ackland, Stephen ; Chiclana, Francisco ; Istance, Howell ; Coupland, Simon

International journal of computer vision, 2019-06, Vol.127 (6-7), p.579-598 [Periódico revisado por pares]

New York: Springer US

Texto completo disponível

Citações Citado por

Enviar para

Título:
Real-Time 3D Head Pose Tracking Through 2.5D Constrained Local Models with Local Neural Fields
Autor: Ackland, Stephen ; Chiclana, Francisco ; Istance, Howell ; Coupland, Simon
Assuntos: Algorithms ; Analysis ; Artificial Intelligence ; Computer Imaging ; Computer Science ; Computer vision ; Deformation ; Electronic devices ; Formability ; Image Processing and Computer Vision ; Jacobi matrix method ; Jacobian matrix ; Machine learning ; Machine vision ; Mathematical models ; Mobile devices ; Optimization ; Parameter estimation ; Pattern Recognition ; Pattern Recognition and Graphics ; Real time ; Robustness (mathematics) ; Streaming media ; Tablet computers ; Texture ; Three dimensional models ; Two dimensional models ; Video data ; Vision
É parte de: International journal of computer vision, 2019-06, Vol.127 (6-7), p.579-598
Descrição: Tracking the head in a video stream is a common thread seen within computer vision literature, supplying the research community with a large number of challenging and interesting problems. Head pose estimation from monocular cameras is often considered an extended application after the face tracking task has already been performed. This often involves passing the resultant 2D data through a simpler algorithm that best fits the data to a static 3D model to determine the 3D pose estimate. This work describes the 2.5D constrained local model, combining a deformable 3D shape point model with 2D texture information to provide direct estimation of the pose parameters, avoiding the need for additional optimization strategies. It achieves this through an analytical derivation of a Jacobian matrix describing how changes in the parameters of the model create changes in the shape within the image through a full-perspective camera model. In addition, the model has very low computational complexity and can run in real-time on modern mobile devices such as tablets and laptops. The point distribution model of the face is built in a unique way, so as to minimize the effect of changes in facial expressions on the estimated head pose and hence make the solution more robust. Finally, the texture information is trained via local neural fields—a deep learning approach that utilizes small discriminative patches to exploit spatial relationships between the pixels and provide strong peaks at the optimal locations.
Editor: New York: Springer US
Idioma: Inglês

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Real-Time 3D Head Pose Tracking Through 2.5D Constrained Local Models with Local Neural Fields

Ackland, Stephen ; Chiclana, Francisco ; Istance, Howell ; Coupland, Simon

New York: Springer US

Buscando em bases de dados remotas. Favor aguardar.