Simultaneous Estimation of Head Pose and Shape by Hierarchical Control System
نویسندگان
چکیده
The present paper proposes a simultaneous estimation of both human head pose and shape. When head pose is estimated for a generic face model, a considerable estimation error is generated by the shape difference between the model and the target face. In the proposed framework, a specific face model is gradually created for the target face by deforming the generic model based on an error analysis. These tasks are controlled by a hierarchical attention control system. Stable and efficient estimation is realized by switching the processes in a hierarchical control system. Experimental results show that the proposed system can simultaneously estimate head pose and shape for several persons. mission l a y >
منابع مشابه
Tracking and Shape Control of a Micro-cantilever using Electrostatic Actuation
In this paper the problems of state estimation, tracking control and shape control in a micro-cantilever beam with nonlinear electrostatic actuation are investigated. The system’s partial differential equation of motion is converted into a set of ordinary differential equations by projection method. Observabillity of the system is proven and a state estimation system is designed using extended ...
متن کاملHead pose estimation without manual initialization
This paper describes a fully automatic system for recovering the rigid components of head pose. It follows the conventional approach of tracking pose changes relative to a reference configuration. Rather than being supplied manually, here the reference configuration is determined by directly estimating pose from the image when the head is close to a frontal presentation. Tracking of pose is don...
متن کاملModel-Free Head Pose Estimation Based on Shape Factorisation and Particle Filtering
Head pose estimation is essential for several applications and is particularly required for head pose-free eye-gaze tracking where estimation of head rotation permits free head movement during tracking. While the literature is broad, the accuracy of recent vision-based head pose estimation methods is contingent upon the availability of training data or accurate initialisation and tracking of sp...
متن کاملFace Alignment Assisted by Head Pose Estimation
In this paper we propose supervised initialisation scheme for cascaded face alignment based on explicit head pose estimation. We first investigate the failure cases of most state of the art face alignment approaches and observe that these failures often share one common global property, i.e. the head pose variation is usually large. Inspired by this, we propose a deep convolutional network mode...
متن کاملSimultaneous Pose Estimation of Multiple People using Multiple-View Cues with Hierarchical Sampling
We present a novel method for dynamic estimation of pose of multiple people using multiple video cameras. Tracking is performed using a model-based approach and a set of cues which exploit both shape and colour information. For shape we propose a fast line-search method to incorporate multi-view constraints without the computational overhead of a voxel representation. The tracking algorithm is ...
متن کامل