An efficient iterative pose estimation algorithm

Or, Siu-Hang; Luk, Wai-Shing; Wong, Kevin; King, Irwin

doi:10.1016/s0262-8856(97)00073-5

Cited by 23 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pose estimation and the model adaptation were achieved synchronously using geometrical measurements. As the 3D models used in [27,28] are simple and rough, these methods cannot achieve accurate pose estimation, especially they cannot estimate seesaw rotation of faces. Recently, Blanz et al [21,22] built a 3D morphable face model from a large set of real 3D face data for pose invariant face recognition.…”

Section: Introductionmentioning

confidence: 99%

3D model-based pose invariant face recognition from multiple views

2007

View full text Add to dashboard Cite

A 3D model-based pose invariant face recognition method that can recognise a human face from its multiple views is proposed. First, pose estimation and 3D face model adaptation are achieved by means of a three-layer linear iterative process. Frontal view face images are synthesised using the estimated 3D models and poses. Then the discriminant 'waveletfaces' are extracted from these synthesised frontal view images. Finally, corresponding nearest feature space classifier is implemented. Experimental results show that the proposed method can recognise faces under variable poses with good accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

3D model-based pose invariant face recognition from multiple views

2007

View full text Add to dashboard Cite

show abstract

“…A number of pose estimation algorithms have been proposed in the literature [11], [14], and [15]. The pose estimation algorithm we used is based on the work by Lowe [12].…”

Section: Introductionmentioning

confidence: 99%

Model reconstruction and pose acquisition using extended Lowe's method

Chang

Wong

2005

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Finding the pose and structure of an unknown object from an image sequence has many applications in graphics, virtual reality, and multimedia processing. In this paper, we address this problem by using a two-stage iterative method. Starting from an initial guess of the structure, the first stage estimates the pose of the object. The second stage uses the estimated pose information to refine the structure. This process is repeated until the difference between the observed data and data re-projected from the estimated model is minimized. This method is a variation of the classical bundle adjustment method, but is faster in execution and is simpler to implement. We used the Kanade-Lucas-Tomasi feature tracker for obtaining the image features. Synthetic and real data have been tested with good results.Index Terms-3-D structure acquisition, bundle adjustment, Lowe's method, pose estimation, structure from motion.

show abstract

“…As formulated in Or [13], this problem is to compute the pose of an object given the three-dimensional structure of the object being investigated is known and its two-dimensional projected image is available. Some techniques have been developed by previous researches to solve this problem.…”

Section: Introductionmentioning

confidence: 99%

“…As for examples, the perspective projection is approximated by a scaled orthographic projection in [16,17]. Or [13] approximates the depths of model points with their perpendicular projections on their inverse projection rays. Nonlinear optimization methods [18][19], however, are dependent of the initial guess.…”

Section: Introductionmentioning

confidence: 99%