Robust Model-Based 3D Head Pose Estimation

Meyer, Gregory P.; Gupta, Shalini; Frosio, Iuri; Reddy, D. V.; Kautz, Jan

doi:10.1109/iccv.2015.416

Cited by 95 publications

(88 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. According to [24], we can classify existing computer vision based head pose estimation methods into two categories: learning based methods [1][2][3] [16] [25][26][27][28][29][30][31][32][33][34][35][36][37][38] that need large amount of training data and computational resources and geometry based methods [4][5][6][7][8][9][10] [ [39][40][41][42][43][44][45][46][47][48][49] that are fast but with a little lower accuracy, see section II for details. In this paper, as shown in Fig.…”

mentioning

confidence: 99%

Single image-based head pose estimation with spherical parametrization and 3D morphing

Yuan

Hou

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

mentioning

confidence: 99%

Single image-based head pose estimation with spherical parametrization and 3D morphing

Yuan

Hou

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

“…Classifier-based methods can achieve good accuracy on high and low quality depth data [4,5], but they usually require extensive training with large datasets, which also cannot generalize well to different 3D sensor. 3D head model methods are more robust to other methods [7], but they require offline initialization from the user to construct personspecific reference models.…”

Section: Depth-based Methodsmentioning

confidence: 99%

Accurate 3D Head Pose Estimation with noisy RGBD images

Zhong

Qin

2016

Proceedings of the 33rd Computer Graphics International

View full text Add to dashboard Cite

In this paper we propose a novel method for accurate 3D head pose estimation with noisy depth map and higher-resolution color image, which typically produced by popular RGBD cameras such as Kinect. Our method combines the benefit of higher-resolution RGB image and 3D information of depth image. For better accuracy and robustness, features are detected and matched with only color images, the outliers are filtered with depth information. In this way it effectively avoids the influence of depth noise. Several effective outlier filtering rules are introduced. Finally the pose parameters are optimized iteratively using Extended LM (Levenberg-Marquardt) method. To evaluate our method, we built a database of more than 10K RGBD images, with ground-truth poses recorded using motion capture. Both qualitative and quantitative evaluations show that our method produces significant less error than previous methods.

show abstract

“…This registration was treated as an optimization problem that was solved through Particle Swarm Optimization (PSO). One more approache based on PSO was presented by Meyer et al [9]. They performed pose estimation by registering a morphable face model to the measured depth data, using a combination of particle swarm optimization (PSO) and the iterative closest point (ICP) algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…While that classification included both 2D and 3D methods, in this paper we focus on head estimation based exclusively on depth information. This considerably reduces the number of categories to: geometric methods [3], [4], appearance methods [5], [6], [7], regression methods [8], flexible models [9], [10] and tracking methods [5].…”

Section: Introductionmentioning

confidence: 99%

Head Pose Estimation Based on 3-D Facial Landmarks Localization and Regression

Derkach

Ruiz

Sukno

2017

2017 12th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2017)

View full text Add to dashboard Cite

Abstract-In this paper we present a system that is able to estimate head pose using only depth information from consumer RGB-D cameras such as Kinect 2. In contrast to most approaches addressing this problem, we do not rely on tracking and produce pose estimation in terms of pitch, yaw and roll angles using single depth frames as input. Our system combines three different methods for pose estimation: two of them are based on state-ofthe-art landmark detection and the third one is a dictionarybased approach that is able to work in especially challenging scans where landmarks or mesh correspondences are too difficult to obtain. We evaluated our system on the SASE database, which consists of ∼30K frames from 50 subjects. We obtained average pose estimation errors between 5 and 8 degrees per angle, achieving the best performance in the FG2017 Head Pose Estimation Challenge. Full code of the developed system is available on-line.

show abstract

Robust Model-Based 3D Head Pose Estimation

Cited by 95 publications

References 30 publications

Single image-based head pose estimation with spherical parametrization and 3D morphing

Single image-based head pose estimation with spherical parametrization and 3D morphing

Accurate 3D Head Pose Estimation with noisy RGBD images

Head Pose Estimation Based on 3-D Facial Landmarks Localization and Regression

Contact Info

Product

Resources

About