Attention Span Prediction Using Head-Pose Estimation With Deep Neural Networks

Abstract

Automated human pose estimation is evolving as an exciting research area in human activity detection. It includes sophisticated applications such as malpractice detection in the examination, distracted driving, gesture detection, etc., and requires robust and reliable pose estimation techniques. These applications help to map the attention of the user with head pose estimation (HPE) metrics supported by emotion and gaze analysis. This paper solves the problem of attention score estimation with HPE. The proposed method ensures ease of implementation while addressing head pose estimation using 68 facial features. Further, to attain reliability and precision, head pose estimation has been implemented as a regression task. The coordinate pair angle method (CPAM) with deep neural network (DNN) regression and elastic net regression is carried out. The use of DNN ensures precision on low lighting, distorted or occluded images. CPAM methodology leverages facial landmark detection and angular difference to estimate head pose. Experimentation results showed that the proposed model could handle large datasets, real-time data processing, significant pose variations, partial occlusions, and diverse facial expressions with a mean absolute error (MAE) of 3° and less. The proposed system was evaluated on three standard databases: the 300W across large poses (300W-LP) dataset, annotated facial landmarks in the wild (AFLW2000) dataset, and the national institute of mental health child emotional faces picture set (NIMH-ChEFS) dataset. The results achieved are on par with recent state-of-the-art methodologies such as anisotropic angle distribution learning (AADL), joint head pose estimation and face alignment algorithm (JFA), rotation axis focused attention network (RAFA-Net), and propose an MAE ranging up to 6°. The paper could achieve remarkable results for attention span prediction using head pose estimation and for many possible future applications.

Camper’s Plane Localization and Head Pose Estimation Based on Multi-View RGBD Sensors

“…A deep task reduction-guided image regularization module is integrated with an anchor-guided pose estimation module, and the HPE problem is formulated as a unified end-to-end learning framework. ElasticNet and DCNN were used for HPE respectively in [24], and the obtained results were then combined with the proposed coordinate pair angle method (CPAM) method to provide results with high accuracy. A multi-stream multitask deep neural network was proposed in [25] for human detection and head pose estimation in RGB-D videos.…”

a approach of query audience’s attention in virtual speech

“…We believe that when a person is in a state of concentration, the head will keep facing the direction of screen and rarely turn significantly. Therefore, when it is detected that the absolute values of yaw and pitch are both in the range of [0°, 10°], it is considered that the audience is in high concentration, when one of the two value is in the range of (10°, 30°] and the other is less than 30°, it belongs to medium concentration, while when one of these is in the range of (30°, 90°], it belongs to low concentration 43 . Then fixation detection is performed, and we judge the behavior that the gaze stays in a small area for more than 500ms as a fixation.…”

Enhancing the Breast Histopathology Image Analysis for Cancer Detection Using Variational Autoencoder

“…The research findings show that there is a 91.3% accuracy for the four-class classification. In, to resolve the two-class breast cancer classification in terms of pathology pictures, offered BiCNN, a revolutionary deep convolution-network-based breast cancer histopathological classification technique [31][32][33]. The category and subcategory labels for breast cancer are taken into account in this deep learning model as previous learning, which can limit the distance between the features in various cancer pathologies.…”