Head Pose Estimation by Perspective-n-Point Solution Based on 2D Markerless Face Tracking

Rocca, François; Mancaş, Matei; Gosselin, Bernard

doi:10.1007/978-3-319-08189-2_8

Cited by 16 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also have similar errors for these methods. A previous study has shown that the Facetracker method gives very good result for a distance under 1 meter [10]. At this distance the KinectSDK is not able to track the head because on one hand the sensor had a blind zone up to 60cm [21] and on the other hand the field of view is too small and it is hard to detect correctly a user under a distance of 1 meter.…”

Section: Face Direction Methods Analysismentioning

confidence: 99%

“…The face tracking part of this method was developed by Jason Saragih and it is known under the name of "FaceTracker" [9]. The head pose estimation part was developed separately and it is explained in a study of this method for computer uses [10].…”

Section: Head Pose Estimationmentioning

confidence: 99%

“…The approach is an instance of the constrained local model with the subspace constrained mean-shifts algorithm as an optimization strategy [10].…”

Section: Webcam Solution (Facetracker)mentioning

confidence: 99%

See 2 more Smart Citations

Head pose estimation & TV Context: current technology

Rocca¹,

Mancaş²,

Grisard³

et al. 2015

EAI Endorsed Transactions on Creative Technologies

Self Cite

View full text Add to dashboard Cite

With the arrival of low-cost high quality cameras, implicit user behaviour tracking is easier and it becomes very interesting for viewer modelling and content personalization in a TV context. In this paper, we present a comparison between three common algorithms of automatic head direction extraction for a person watching TV in a realistic context. Those algorithms compute the different rotation angles of the head (pitch, roll, yaw) in a non-invasive and continuous way based on 2D and/or 3D features acquired with low cost cameras. These results are compared with a reference based on the Qualisys motion capture commercial system which is a robust marker-based tracking system. The performances of the different algorithms are compared function of different configurations. While our results show that full implicit behaviour tracking in real-life TV setups is still a challenge, with the arrival of next generation sensors (as the new Kinect one sensor), accurate TV personalization based on implicit behaviour is close to become a very interesting option.

show abstract

Section: Face Direction Methods Analysismentioning

confidence: 99%

Section: Head Pose Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Head pose estimation & TV Context: current technology

Rocca¹,

Mancaş²,

Grisard³

et al. 2015

EAI Endorsed Transactions on Creative Technologies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Algorithms such as POSIT [39] and Perspective-n-Points [40] were used to deduce rotation matrices from landmarks and convert them into pose values. The construction of datasets was challenging because it was necessary to label the Euler angles accurately.…”

Section: Head Pose Estimationmentioning

confidence: 99%

Multitask Learning Strategy with Pseudo-Labeling: Face Recognition, Facial Landmark Detection, and Head Pose Estimation

Lee,

Jang,

Bae

et al. 2024

Sensors

View full text Add to dashboard Cite

Most facial analysis methods perform well in standardized testing but not in real-world testing. The main reason is that training models cannot easily learn various human features and background noise, especially for facial landmark detection and head pose estimation tasks with limited and noisy training datasets. To alleviate the gap between standardized and real-world testing, we propose a pseudo-labeling technique using a face recognition dataset consisting of various people and background noise. The use of our pseudo-labeled training dataset can help to overcome the lack of diversity among the people in the dataset. Our integrated framework is constructed using complementary multitask learning methods to extract robust features for each task. Furthermore, introducing pseudo-labeling and multitask learning improves the face recognition performance by enabling the learning of pose-invariant features. Our method achieves state-of-the-art (SOTA) or near-SOTA performance on the AFLW2000-3D and BIWI datasets for facial landmark detection and head pose estimation, with competitive face verification performance on the IJB-C test dataset for face recognition. We demonstrate this through a novel testing methodology that categorizes cases as soft, medium, and hard based on the pose values of IJB-C. The proposed method achieves stable performance even when the dataset lacks diverse face identifications.

show abstract

“…Key points such as the eye, nose, and mouth position are selected. Then, the Perspective-n-Point (PnP) algorithm is applied to compute the pose transformation from the face coordinate to the world coordinate [18]. Hence, we can calculate the orientation angles of the driver's head, including yaw, pitch, and roll.…”

Section: Driver's Head Posture Recognitionmentioning

confidence: 99%

An Intelligent Chinese Driver Road Performance Assessment Model (RPAM) for Future Licensing Examinations

Gong,

Zhang,

Liu

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

As the demand for private vehicles rises, there has been a gradual increase in the number of motor vehicles on the roads, leading to a growing concern about addressing traffic safety. Currently, China’s approach to assessing driver capabilities remains rooted in traditional, non-intelligent, and standardized evaluation methods based on examination subjects. The traditional model often falls short in providing constructive feedback on a driver’s real-world vehicle handling abilities, as many of the examination subjects can be practiced in advance to achieve a mere passing result, which, undoubtedly, increases the likelihood of underqualified drivers on the road. To address the issues of the current examination-oriented driver evaluation system in China, we propose a road performance assessment model (RPAM) that assesses drivers comprehensively by evaluating their road environment perception and vehicle operation abilities based on an in-vehicle and out-vehicle perception system. The model leverages patterns of the driver’s head posture, along with real-time information on the vehicle’s behavior and the road conditions, to quantify various performance metrics related to reasonable operation processes. These metrics are then integrated to generate a holistic assessment of the driving capabilities. This paper ultimately conducted tests of the RPAM on one actual examination route in Beijing. Two drivers were randomly selected for the examination. The model successfully computed the overall ability scores for each driver, validating the effectiveness.

show abstract

Head Pose Estimation by Perspective-n-Point Solution Based on 2D Markerless Face Tracking

Cited by 16 publications

References 6 publications

Head pose estimation & TV Context: current technology

Head pose estimation & TV Context: current technology

Multitask Learning Strategy with Pseudo-Labeling: Face Recognition, Facial Landmark Detection, and Head Pose Estimation

An Intelligent Chinese Driver Road Performance Assessment Model (RPAM) for Future Licensing Examinations

Contact Info

Product

Resources

About