Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Jose Celestino et al.
Summary: This work proposes a novel deep learning approach for head pose estimation under occlusions, achieving better performance than existing methods. The approach is based on latent space regression and demonstrates effectiveness through experiments on different datasets and real-life scenarios.
PATTERN RECOGNITION
(2023)
Article
Engineering, Civil
Weiheng Chai et al.
Summary: Driver behavior analysis is crucial in driver assistance systems, especially in understanding the driver's attention and concentration. However, data collected in naturalistic driving studies (NDS) often have lower quality videos and more challenging camera positions. In this study, we propose three approaches using facial key points to classify a driver's head pose from side-view videos. We compare these approaches with baselines using leave-one-driver-out cross-validation and find that the proposed method using BiGRU achieves an 11% improvement in overall accuracy compared to the best performing baseline.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Markus Roth et al.
Summary: IntrApose is a novel method for continuous head pose estimation from a single camera image, which utilizes camera intrinsics and a continuous rotation representation to improve accuracy.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Engineering, Electrical & Electronic
Niklas Alexander Koehler et al.
Summary: Great progress has been made in contactless detection of infant and child respiratory motion in recent decades. However, depth cameras used in this field can be affected by systematic errors and environmental influences, which can greatly impact the signal quality. This study aims to assess the robustness of various depth cameras in clinical and home settings, considering factors such as viewing angles, reflectivity, and infrared light. The results show that three cameras achieved adequate performance in correlating depth images with respiratory-belt signals, while others failed under certain ambient conditions. Therefore, careful camera selection considering environmental influences is crucial.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Artificial Intelligence
Yueying Kao et al.
Summary: This paper proposes a deep neural network called PerspNet for single-image 3D face reconstruction under perspective projection. It simultaneously reconstructs the 3D face shape in canonical space and learns the correspondence between 2D pixels and 3D points, enabling estimation of the 6DoF face pose. A large ARKitFace dataset with ground-truth 3D face mesh and annotated pose parameters is also contributed for training and evaluation. Experimental results demonstrate the superior performance of the proposed approach.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Yuanquan Xu et al.
Summary: This paper proposes head pose estimation using deep neural networks and 3D point cloud, achieving outstanding performance in accurately estimating 3D head poses by classifying them into 36 classes and predicting the probability of each angle in a class using multi-layer perceptron. The method is lightweight and computationally efficient, outperforming state-of-the-art ones in terms of accuracy.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Andrea F. Abate et al.
Summary: Biometric based systems are widely used in various fields, and head pose estimation is one of them, which can be applied in driver attention detection and face frontalization tasks. This survey provides an overview of the involved datasets, recent techniques, and applications, and evaluates and compares different methods.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Jiahao Xia et al.
Summary: The study introduces an efficient multitask neural network ATPN for face alignment, face tracking, and head pose estimation. ATPN improves performance in face alignment with shortcut connections and enhances other tasks with heatmap fusion, while also saving time in face detection and increasing real-time capability for video tasks.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Review
Robotics
Steven Macenski et al.
Summary: This article discusses the development of the Robot Operating System (ROS) and the importance of ROS 2, as well as its impact on accelerating reliable deployment of robot systems.
Article
Engineering, Civil
Tiancheng Hu et al.
Summary: The study proposes a novel temporal deep learning model for head pose estimation from point cloud data, extracting discriminative feature representation directly from the 3D spatial structure of the face and training on the MDM dataset with BLSTM layers. It achieves better results compared to non-temporal algorithms using point cloud data, and state-of-the-art models using RGB images, showing that incorporating temporal information not only improves accuracy, but also increases the smoothness of predictions.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Chien Thai et al.
Summary: This study proposes a lightweight multi-task model called MHPNet, which can simultaneously address head pose estimation and masked face classification problems. Through knowledge distillation training on joint datasets, the model achieves significant improvements in performance and accuracy.
INFORMATION SCIENCES
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Naina Dhingra
Summary: This paper presents a lightweight network for head pose estimation task, which combines depthwise separable convolutional and transformer encoder layers to efficiently learn head poses and reduce parameter space. Experimental results demonstrate that this network outperforms previous lightweight networks in terms of mean absolute error and parameter count, making it suitable for mobile devices.
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Hai Liu et al.
Summary: The paper introduces a novel anisotropic angle distribution learning (AADL) network for head pose estimation task, which constructs anisotropic angle distribution labels and measures the difference between predicted labels and groundtruth labels using Kullback-Leibler divergence. Experimental results demonstrate that the proposed method performs well in handling head pose image missing and motion blur.
Article
Computer Science, Artificial Intelligence
C. Hari et al.
Summary: This work introduces a method for analyzing driver distraction based on face pose cues, utilizing a face pose database of vehicle drivers and employing Gabor features and an SVM classifier, yielding superior results compared to deep learning and other manifold methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Oncology
Giovanni Fattori et al.
Summary: The Polaris product line from Northern Digital Inc. is known for accurate optical tracking measurements, with the new Vega model replacing the Spectra sensor and showing improved performance in static and dynamic measurements in radiation therapy integration. Clinical tests have confirmed the safety and efficacy of the Polaris Vega for monitoring breathing motion and patient positioning.
RADIATION ONCOLOGY
(2021)
Article
Chemistry, Multidisciplinary
Redhwan Algabri et al.
Summary: This paper presents an extended work on online learning framework for trajectory prediction and recovery, integrated with a deep learning-based person-following system. The proposed framework allows the robot to track and predict the trajectory of a specific person while avoiding obstacles in real-time, demonstrating effectiveness in realistic environments.
APPLIED SCIENCES-BASEL
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Vitor Albiero et al.
Summary: The research introduces a real-time, 3D face pose estimation method that does not require face detection or landmark localization, outperforming existing techniques by leveraging 6DoF pose. The approach is based on a Faster R-CNN model, which is easy to train and efficient, effectively improving the accuracy of face pose estimation.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Miao Xin et al.
Summary: This paper proposes a strong baseline method which views head pose estimation as a graph regression problem and utilizes Graph Convolutional Networks to model complex mappings. Introducing mechanisms like EVA, ACA, and DCA further enhances performance, with experiment results showing superiority over state-of-the-art landmark-based and landmark-free methods.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhiwen Cao et al.
Summary: This paper proposes a new approach using three vectors to describe head poses and develops a neural network model based on this representation. By introducing Mean Absolute Error of Vectors (MAEV) as the performance measurement and training the network with orthogonality constraints, it effectively addresses the issues in current head pose estimation and achieves state-of-the-art results on public datasets.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
(2021)
Article
Computer Science, Artificial Intelligence
Daniel Lopez-Sanchez et al.
Article
Computer Science, Artificial Intelligence
Bin Huang et al.
IMAGE AND VISION COMPUTING
(2020)
Article
Chemistry, Analytical
Redhwan Algabri et al.
Proceedings Paper
Computer Science, Artificial Intelligence
Bjorn Browatzki et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Artificial Intelligence
Yue Wu et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2019)
Article
Computer Science, Artificial Intelligence
Feng-Ju Chang et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Tsun-Yi Yang et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Nataniel Ruiz et al.
PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiangyu Zhu et al.
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2016)
Article
Computer Science, Artificial Intelligence
Gabriele Fanelli et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2013)
