Optical tracking of head pose via fiducial markers has been proven to enable effective correction of motion artifacts in the brain during magnetic resonance imaging but remains difficult to implement in the clinic due to lengthy calibration and set up times. Advances in deep learning for markerless head pose estimation have yet to be applied to this problem because of the sub-millimetre spatial resolution required for motion correction. In the present work, two optical tracking systems are described for the development and training of a neural network: one marker-based system (a testing platform for measuring ground truth head pose) with high tracking fidelity to act as the training labels, and one markerless deep-learning-based system using images of the markerless head as input to the network. The markerless system has the potential to overcome issues of marker occlusion, insufficient rigid attachment of the marker, lengthy calibration times, and unequal performance across degrees of freedom (DOF), all of which hamper the adoption of marker-based solutions in the clinic. Detail is provided on the development of a custom moiré-enhanced fiducial marker for use as ground truth and on the calibration procedure for both optical tracking systems. Additionally, the development of a synthetic head pose dataset is described for the proof of concept and initial pre-training of a simple convolutional neural network. Results indicate that the ground truth system has been sufficiently calibrated and can track head pose with an error of <1 mm and <1°. Tracking data of a healthy, adult participant are shown. Pre-training results show that the average root-mean-squared error across the 6 DOF is 0.13 and 0.36 (mm or degrees) on a head model included and excluded from the training dataset, respectively. Overall, this work indicates excellent feasibility of the deep-learning-based approach and will enable future work in training and testing on a real dataset in the MRI environment.

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.

In this paper, we propose a learning state evaluation method based on face detection and head pose estimation. This method is suitable for mobile devices with weak computing power, so it is necessary to control the parameter quantity of the face detection and head pose estimation network. Firstly, we propose a ghost and attention module (GA) base face detection network (GA-Face). GA-Face reduces the number of parameters and computation in the feature extraction network through the ghost module, and focuses the network on important features through a parameter-free attention mechanism. We also propose a lightweight dual-branch (DB) head pose estimation network: DB-Net. Finally, we propose a student learning state evaluation algorithm. This algorithm can evaluate the learning status of students based on the distance between their faces and the screen, as well as their head posture. We validate the effectiveness of the proposed GA-Face and DB-Net on several standard face detection datasets and standard head pose estimation datasets. Finally, we validate, through practical cases, that the proposed online learning state assessment method can effectively assess the level of student attention and concentration, and, due to its low computational complexity, will not interfere with the student\'s learning process.

Head pose estimation serves various applications, such as gaze estimation, fatigue-driven detection, and virtual reality. Nonetheless, achieving precise and efficient predictions remains challenging owing to the reliance on singular data sources. Therefore, this study introduces a technique involving multimodal feature fusion to elevate head pose estimation accuracy. The proposed method amalgamates data derived from diverse sources, including RGB and depth images, to construct a comprehensive three-dimensional representation of the head, commonly referred to as a point cloud. The noteworthy innovations of this method encompass a residual multilayer perceptron structure within PointNet, designed to tackle gradient-related challenges, along with spatial self-attention mechanisms aimed at noise reduction. The enhanced PointNet and ResNet networks are utilized to extract features from both point clouds and images. These extracted features undergo fusion. Furthermore, the incorporation of a scoring module strengthens robustness, particularly in scenarios involving facial occlusion. This is achieved by preserving features from the highest-scoring point cloud. Additionally, a prediction module is employed, combining classification and regression methodologies to accurately estimate head poses. The proposed method improves the accuracy and robustness of head pose estimation, especially in cases involving facial obstructions. These advancements are substantiated by experiments conducted using the BIWI dataset, demonstrating the superiority of this method over existing techniques.

Head pose estimation is an important technology for analyzing human behavior and has been widely researched and applied in areas such as human-computer interaction and fatigue detection. However, traditional head pose estimation networks suffer from the problem of easily losing spatial structure information, particularly in complex scenarios where occlusions and multiple object detections are common, resulting in low accuracy. To address the above issues, we propose a head pose estimation model based on the residual network and capsule network. Firstly, a deep residual network is used to extract features from three stages, capturing spatial structure information at different levels, and a global attention block is employed to enhance the spatial weight of feature extraction. To effectively avoid the loss of spatial structure information, the features are encoded and transmitted to the output using an improved capsule network, which is enhanced in its generalization ability through self-attention routing mechanisms. To enhance the robustness of the model, we optimize Huber loss, which is first used in head pose estimation. Finally, experiments are conducted on three popular public datasets, 300W-LP, AFLW2000, and BIWI. The results demonstrate that the proposed method achieves state-of-the-art results, particularly in scenarios with occlusions.

Drowsiness-related car accidents continue to have a significant effect on road safety. Many of these accidents can be eliminated by alerting the drivers once they start feeling drowsy. This work presents a non-invasive system for real-time driver drowsiness detection using visual features. These features are extracted from videos obtained from a camera installed on the dashboard. The proposed system uses facial landmarks and face mesh detectors to locate the regions of interest where mouth aspect ratio, eye aspect ratio, and head pose features are extracted and fed to three different classifiers: random forest, sequential neural network, and linear support vector machine classifiers. Evaluations of the proposed system over the National Tsing Hua University driver drowsiness detection dataset showed that it can successfully detect and alarm drowsy drivers with an accuracy up to 99%.

In recent years, the pandemic situation has forced the education system to shift from traditional teaching to online teaching or blended learning. The ability to monitor remote online examinations efficiently is a limiting factor to the scalability of this stage of online evaluation in the education system. Human Proctoring is the most used common approach by either asking learners to take a test in the examination centers or by monitoring visually asking learners to switch on their camera. However, these methods require huge labor, effort, infrastructure, and hardware. This paper presents an automated AI-based proctoring system- \'Attentive system\' for online evaluation by capturing the live video of the examinee. Our Attentive system includes four components to estimate the malpractices such as face detection, multiple person detection, face spoofing, and head pose estimation. Attentive Net detects the faces and draws bounding boxes along with confidences. Attentive Net also checks the alignment of the face using the rotation matrix of Affine Transformation. The face net algorithm is combined with Attentive-Net to extract landmarks and facial features. The process for identifying spoofed faces is initiated only for aligned faces by using a shallow CNN Liveness net. The head pose of the examiner is estimated by using the SolvePnp equation, to check if he/she is seeking help from others. Crime Investigation and Prevention Lab (CIPL) datasets and customized datasets with various types of malpractices are used to evaluate our proposed system. Extensive Experimental results demonstrate that our method is more accurate, reliable and robust for proctoring system that can be practically implemented in real time environment as Automated proctoring System. An improved accuracy of 0.87 is reported by authors with the combination of Attentive Net, Liveness net and head pose estimation.

Face recognition plays the significant role in many human-computer interaction decvices and applications, whose access control systems are based on the verification of face biometrical features. Though great improvement in the recognition performances have been achieved, when under some specific conditions like faces with occlusions, the performance would suffer a severe drop. Occlusion is one of the most significant reasons for the performance degrade of the existing general face recognition systems. The biggest problem in occluded face recognition (OFR) lies in the lack of the occluded face data. To mitigate this problem, this paper has proposed one new OFR network DOMG-OFR (Dynamic Occlusion Mask Generator based Occluded Face Recognition), which keeps trying to generate the most informative occluded face training samples on feature level dynamically, in this way, the recognition model would always be fed with the most valuable training samples so as to save the labor in preparing the synthetic data while simultaneously improving the training efficiency. Besides, this paper also proposes one new module called Decision Module (DM) in an attempt to combine both the merits of the two mainstream methodologies in OFR which are face image reconstruction based methodologies and the face feature filtering based methodologies. Furthermore, to enable the existing face deocclusion methods that mostly target at near frontal faces to work well on faces under large poses, one head pose aware deocclusion pipeline based on the Condition Generative Adversarial Network (CGAN) is proposed. In the experimental parts, we have also investigated the effects of the occlusions upon face recognition performance, and the validity and the efficiency of our proposed Decision based OFR pipeline has been fully proved. Through comparing both the verification and the recognition performance upon both the real occluded face datasets and the synthetic occluded face datasets with other existing works, our proposed OFR architecture has demonstrated obvious advantages over other works.

Mainstream methods treat head pose estimation as a supervised classification/regression problem, whose performance heavily depends on the accuracy of ground-truth labels of training data. However, it is rather difficult to obtain accurate head pose labels in practice, due to the lack of effective equipment and reasonable approaches for head pose labeling. In this paper, we propose a method which does not need to be trained with head pose labels, but matches the keypoints between a reconstructed 3D face model and the 2D input image, for head pose estimation. The proposed head pose estimation method consists of two components: the 3D face reconstruction and the 3D-2D matching keypoints. At the 3D face reconstruction phase, a personalized 3D face model is reconstructed from the input head image using convolutional neural networks, which are jointly optimized by an asymmetric Euclidean loss and a keypoint loss. At the 3D-2D keypoints matching phase, an iterative optimization algorithm is proposed to match the keypoints between the reconstructed 3D face model and the 2D input image efficiently under the constraint of perspective transformation. The proposed method is extensively evaluated on five widely used head pose estimation datasets, including Pointing\'04, BIWI, AFLW2000, Multi-PIE, and Pandora. The experimental results demonstrate that the proposed method achieves excellent cross-dataset performance and surpasses most of the existing state-of-the-art approaches, with average MAEs of 4.78∘ on Pointing\'04, 6.83∘ on BIWI, 7.05∘ on AFLW2000, 5.47∘ on Multi-PIE, and 5.06∘ on Pandora, although the model of the proposed method is not trained on any of these five datasets.

Accurate face segmentation strongly benefits the human face image analysis problem. In this paper we propose a unified framework for face image analysis through end-to-end semantic face segmentation. The proposed framework contains a set of stack components for face understanding, which includes head pose estimation, age classification, and gender recognition. A manually labeled face data-set is used for training the Conditional Random Fields (CRFs) based segmentation model. A multi-class face segmentation framework developed through CRFs segments a facial image into six parts. The probabilistic classification strategy is used, and probability maps are generated for each class. The probability maps are used as features descriptors and a Random Decision Forest (RDF) classifier is modeled for each task (head pose, age, and gender). We assess the performance of the proposed framework on several data-sets and report better results as compared to the previously reported results.