Estimating head pose orientation using extremely low resolution images

Chen, Jiawei; Wu, Q. M. Jonathan; Richter, Kristi; Konrad, Janusz; Ishwar, Prakash

doi:10.1109/ssiai.2016.7459176

Cited by 40 publications

(21 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, a bunch of methods regard head pose estimation as an optimization problem: in [28] a multi-template, Iterative Closest Point (ICP) [29] based gaze tracking system is introduced. Besides, other works use linear or nonlinear regression with extremely low-resolution images [30]. HOG features and a Gaussian locally-linear mapping model were used in [12] and, finally, recent works produce head pose estimations performing a face alignment task [31] using CNNs.…”

Section: Related Workmentioning

confidence: 99%

Face-from-Depth for Head Pose Estimation on Depth Images

Borghi

Fabbri

Vezzani

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Depth cameras allow to set up reliable solutions for people monitoring and behavior understanding, especially when unstable or poor illumination conditions make unusable common RGB sensors. Therefore, we propose a complete framework for the estimation of the head and shoulder pose based on depth images only. A head detection and localization module is also included, in order to develop a complete end-to-end system. The core element of the framework is a Convolutional Neural Network, called POSEidon + , that receives as input three types of images and provides the 3D angles of the pose as output. Moreover, a Face-from-Depth component based on a Deterministic Conditional GAN model is able to hallucinate a face from the corresponding depth image. We empirically demonstrate that this positively impacts the system performances. We test the proposed framework on two public datasets, namely Biwi Kinect Head Pose and ICT-3DHP, and on Pandora, a new challenging dataset mainly inspired by the automotive setup. Experimental results show that our method overcomes several recent state-of-art works based on both intensity and depth input data, running in real-time at more than 30 frames per second.

show abstract

Section: Related Workmentioning

confidence: 99%

Face-from-Depth for Head Pose Estimation on Depth Images

Borghi

Fabbri

Vezzani

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…HoG features are mapped (through a Gaussian locally linear model) onto the head pose space, which is then used to predict a new head orientation. Chen et al [18] achieve good results with RGB images of low resolution using a Support Vector Regression (SVR) classifier trained with a gradient-based feature. All these methods combine the information in a single model and achieve state-of-the-art (SoA) results when sufficient training data is provided.…”

Section: Rgb-based Approachesmentioning

confidence: 99%

Robust head pose estimation based on key frames for human-machine interaction

Madrigal

Lerasle

2020

J Image Video Proc.

View full text Add to dashboard Cite

Humans can interact with several kinds of machine (motor vehicle, robots, among others) in different ways. One way is through his/her head pose. In this work, we propose a head pose estimation framework that combines 2D and 3D cues using the concept of key frames (KFs). KFs are a set of frames learned automatically offline that consist the following: 2D features, encoded through Speeded Up Robust Feature (SURF) descriptors; 3D information, captured by Fast Point Feature Histogram (FPFH) descriptors; and target's head orientation (pose) in real-world coordinates, which is represented through a 3D facial model. Then, the KF information is re-enforced through a global optimization process that minimizes error in a way similar to bundle adjustment. The KF allows to formulate, in an online process, a hypothesis of the head pose in new images that is then refined through an optimization process, performed by the iterative closest point (ICP) algorithm. This KF-based framework can handle partial occlusions and extreme rotations even with noisy depth data, improving the accuracy of pose estimation and detection rate. We evaluate the proposal using two public benchmarks in the state of the art: (1) BIWI Kinect Head Pose Database and (2) ICT 3D HeadPose Database. In addition, we evaluate this framework with a small but challenging dataset of our own authorship where the targets perform more complex behaviors than those in the aforementioned public datasets. We show how our approach outperforms relevant state-of-the-art proposals on all these datasets.

show abstract

“…In more recent work, [12] develops a deidentification filter on video sequences of car drivers and then estimates a driver's gaze, head dynamic, etc. In [5], a non-linear regression method is proposed to estimate human head pose from extremely low resolution images in which identity is visually imperceptible. However, the aforementioned methods either only produce coarse-grained head pose estimates [14,15,12] or perform below par in head pose estimation [5].…”

Section: Related Workmentioning

confidence: 99%

“…In [5], a non-linear regression method is proposed to estimate human head pose from extremely low resolution images in which identity is visually imperceptible. However, the aforementioned methods either only produce coarse-grained head pose estimates [14,15,12] or perform below par in head pose estimation [5]. Invariant Representation Learning: Invariant representation learning has been extensively studied in various contexts.…”

Section: Related Workmentioning

confidence: 99%

Vae/Wgan-Based Image Representation Learning For Pose-Preserving Seamless Identity Replacement In Facial Images

Kawai

Chen

Ishwar

et al. 2019

2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP)

Self Cite

View full text Add to dashboard Cite

We present a novel variational generative adversarial network (VGAN) based on Wasserstein loss to learn a latent representation from a face image that is invariant to identity but preserves head-pose information. This facilitates synthesis of a realistic face image with the same head pose as a given input image, but with a different identity. One application of this network is in privacy-sensitive scenarios; after identity replacement in an image, utility, such as head pose, can still be recovered. Extensive experimental validation on synthetic and real human-face image datasets performed under 3 threat scenarios confirms the ability of the proposed network to preserve head pose of the input image, mask the input identity, and synthesize a good-quality realistic face image of a desired identity. We also show that our network can be used to perform pose-preserving identity morphing and identitypreserving pose morphing. The proposed method improves over a recent state-of-the-art method in terms of quantitative metrics as well as synthesized image quality.

show abstract

Estimating head pose orientation using extremely low resolution images

Cited by 40 publications

References 9 publications

Face-from-Depth for Head Pose Estimation on Depth Images

Face-from-Depth for Head Pose Estimation on Depth Images

Robust head pose estimation based on key frames for human-machine interaction

Vae/Wgan-Based Image Representation Learning For Pose-Preserving Seamless Identity Replacement In Facial Images

Contact Info

Product

Resources

About