Delaunay Triangulation based 3D Human Face Modeling from Uncalibrated Images

Hassanpour, Reza; Atalay, Volkan

doi:10.1109/cvpr.2004.319

Cited by 8 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of those 56 points, 19 are selected through recursive feature elimination. Based on the face modeling approach in [13], a Delaunay triangulation is computed over these 19 points and the three angles of each of the resulting triangles are added to the feature vector. The triangulation is kept the same for all images, so for most of them the Delaunay property is not maintained.…”

Section: Feature Extraction Normalization and Selectionmentioning

confidence: 99%

Driver Gaze Region Estimation without Use of Eye Movement

et al. 2016

View full text Add to dashboard Cite

Automated estimation of the allocation of a driver's visual attention may be a critical component of future Advanced Driver Assistance Systems. In theory, vision-based tracking of the eye can provide a good estimate of gaze location. In practice, eye tracking from video is challenging because of sunglasses, eyeglass reflections, lighting conditions, occlusions, motion blur, and other factors. Estimation of head pose, on the other hand, is robust to many of these effects, but cannot provide as fine-grained of a resolution in localizing the gaze. However, for the purpose of keeping the driver safe, it is sufficient to partition gaze into regions. In this effort, we propose a system that extracts facial features and classifies their spatial configuration into six regions in real-time. Our proposed method achieves an average accuracy of 91.4% at an average decision rate of 11 Hz on a dataset of 50 drivers from an on-road study.

show abstract

Section: Feature Extraction Normalization and Selectionmentioning

confidence: 99%

Driver Gaze Region Estimation without Use of Eye Movement

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Aside from trivial texture mapping on low quality geometry, several works in the field of 3D reconstruction focus on the reconstruction of 3D faces from images. Very realistic results can be achieved [HA04, D'A01], but the produced geometry is usually not accurate enough. An approach which is more related to our goal is the morphing of face model to fit images [BV99, Bla06, JHY*05] and 3D scans [BSS07].…”

Section: Related Workmentioning

confidence: 99%

Reconstructing head models from photographs for individualized 3D‐audio processing

Dellepiane

Pietroni

Tsingos

et al. 2008

Computer Graphics Forum

View full text Add to dashboard Cite

Visual fidelity and interactivity are the main goals in Computer Graphics research, but recently also audio is assuming an important role. Binaural rendering can provide extremely pleasing and realistic three-dimensional sound, but to achieve best results it's necessary either to measure or to estimate individual Head Related Transfer Function (HRTF). This function is strictly related to the peculiar features of ears and face of the listener. Recent sound scattering simulation techniques can calculate HRTF starting from an accurate 3D model of a human head. Hence, the use of binaural rendering on large scale (i.e. video games, entertainment) could depend on the possibility to produce a sufficiently accurate 3D model of a human head, starting from the smallest possible input. In this paper we present a completely automatic system, which produces a 3D model of a head starting from simple input data (five photos and some key-points indicated by user). The geometry is generated by extracting information from images and accordingly deforming a 3D dummy to reproduce user head features. The system proves to be fast, automatic, robust and reliable: geometric validation and preliminary assessments show that it can be accurate enough for HRTF calculation.

show abstract

“…Therefore, a manual correction procedure is applied to remedy those particular feature points. Subsequently, Delaunay Triangulation [4], [6] is applied to construct the 2D triangles from the features and contour points.…”

Section: St Module: Compiling Successive Facial Images and Finding mentioning

confidence: 99%

Using the Orthographic Projection Model to Approximate the Perspective Projection Model for 3D Facial Reconstruction

Lien

Advances in Image and Video Technology

View full text Add to dashboard Cite

This study develops a 3D facial reconstruction system, which consists of five modules, using the orthographic projection model to approximate the perspective projection model. The first module identifies a number of feature points on the face and tracks these feature points over a sequence of facial images by the optical flow technique. The second module applies the factorization method to the orthographic model to reconstruct a 3D human face. The facial images are acquired using a pinhole camera, which are based on a perspective projection model. However, the face is reconstructed using an orthographic projection model. To compensate for the difference between these two models, the third module implements a simple and efficient method for approximating the perspective projection model. The fourth module overcomes the missing point problem, commonly arising in 3D reconstruction applications. Finally, the fifth module implements a smoothing process for the 3D surface by interpolating additional vertices.

show abstract

Delaunay Triangulation based 3D Human Face Modeling from Uncalibrated Images

Cited by 8 publications

References 17 publications

Driver Gaze Region Estimation without Use of Eye Movement

Driver Gaze Region Estimation without Use of Eye Movement

Reconstructing head models from photographs for individualized 3D‐audio processing

Using the Orthographic Projection Model to Approximate the Perspective Projection Model for 3D Facial Reconstruction

Contact Info

Product

Resources

About