Corpus ID: 12922963

Head pose Estimation Using Convolutional Neural Networks

  title={Head pose Estimation Using Convolutional Neural Networks},
  author={Xingyu Liu},
Head pose estimation is a fundamental problem in computer vision. Several methods has been proposed to solve this problem. Most existing methods use traditional computer vision methods and existing method of using neural networks works on depth bitmaps. In this project, we explore using convolutional neural networks (CNNs) that take RGB image as input to estimate the head pose. We use regression as the estimation approach. We explored the effect of different regularization strength and face… Expand
Head pose estimation in the wild using Convolutional Neural Networks and adaptive gradient methods
The results show that joining CNNs and adaptive gradient methods leads to the state-of-the-art in unconstrained head pose estimation. Expand
Generic and Robust Method for Head Pose Estimation
This paper presents a generic and robust method for model-based global 2D head pose estimation from single RGB Image using the one part the Gabor filters to conceive a robust pose descriptor to illumination and facial expression variations, and that target the pose information. Expand
Face alignment using a deep neural network with local feature learning and recurrent regression
It is found that learning of the good local landmark features in pursuit of good landmark classification also leads to a higher face alignment accuracy and achieves state-of-the-art performance on several public benchmark dataset. Expand
An Optimized Architecture of Image Classification Using Convolutional Neural Network
The convolutional neural network (CNN) is the type of deep neural networks which has been widely used in visual recognition. Over the years, CNN has gained lots of attention due to its highExpand


Face tracking and head pose estimation using convolutional neural networks
A face tracker, adjusted to each person's face chrominance values, and learnt online, is proposed, based on the face bounding box, and only utilizes subsets of classifiers, excluding those corresponding to rotation angles far from the current. Expand
3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network
A deep convolutional neural network for 3D human pose estimation from monocular images is proposed and empirically show that the network has disentangled the dependencies among different body parts, and learned their correlations. Expand
Learning symmetrical model for head pose estimation
A Decision Tree model is trained in order to recognize head pose with regard to the areas of symmetry and it is demonstrated that the change in the size of the regions that contain a bilateral symmetry provides accurate pose estimation. Expand
Human Tracking Using Convolutional Neural Networks
This paper treats tracking as a learning problem of estimating the location and the scale of an object given its previous location, scale, as well as current and previous image frames, and introduces multiple path ways in CNN to better fuse local and global information. Expand
Head Pose Estimation in Computer Vision: A Survey
This paper discusses the inherent difficulties in head pose estimation and presents an organized survey describing the evolution of the field, comparing systems by focusing on their ability to estimate coarse and fine head pose and highlighting approaches well suited for unconstrained environments. Expand
Estimating Head Pose with Neural Networks-Results on the Pointing 04 ICPR Workshop Evaluation Data
In this paper we report the results of a neural network based approach to head pose esimtation on the evaluation data set provided for the Pointing04 ICPR workshop. In the presented approach, we useExpand
Comparative study of coarse head pose estimation
  • L. Brown, Ying-li Tian
  • Computer Science
  • Workshop on Motion and Video Computing, 2002. Proceedings.
  • 2002
This work evaluates two coarse pose estimation schemes, based on (1) a probabilistic model approach and (2) a neural network approach, and compares the results of the two techniques for varying resolution, head localization accuracy and required pose accuracy. Expand
Real-time face pose estimation from single range images
A real-time algorithm to estimate the 3D pose of a previously unseen face from a single range image is presented, based on a novel shape signature to identify noses in range images and a novel error function that compares the input range image to precomputed pose images of an average face model. Expand
Real Time Head Pose Estimation from Consumer Depth Cameras
We present a system for estimating location and orientation of a person's head, from depth data acquired by a low quality device. Our approach is based on discriminative random regression forests:Expand
Face Recognition Using Convolutional Neural Network and Simple Logistic Classifier
A hybrid system is presented in which a convolutional neural network (CNN) and a Logistic regression classifier (LRC) are combined, which shows improved classification rates in smaller amount of time. Expand