Head posture detection with embedded attention model
Authors:
Open Access
- 1 March 2020
- conference paper
- Published by IOP Publishing in IOP Conference Series: Materials Science and Engineering
- Vol. 782 (3)
Abstract
Based on Convolutional Neural Network, the paper presents a compact detection algorithm that can estimate the head pose from a single picture. Our method is based on soft stage wise regression. In order to reduce model complexity, three-dimensional detection of the “pitch, yaw, and roll” of the head posture adopts multi-level classification. Each level of classification requires only a small number of classification tasks and fewer neurons. In order to enhance the feature expression of the algorithm, the attention model is embedded. Attention model includes channel attention structure and spatial attention structure, enhancing the feature expression of the feature map in the two dimensions of the intermediate feature map channel and space. The attention model can be seamlessly integrated into the CNN architecture with low overhead. The experiment proves that the improved algorithm compares the method model proposed by Yang with a smaller complexity of 4.36M and an average absolute error of 0.7%~0.9%.Keywords
This publication has 8 references indexed in Scilit:
- FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Image2019
- A novel deep network architecture for reconstructing RGB facial images from thermal for face recognitionMultimedia Tools and Applications, 2019
- CBAM: Convolutional Block Attention Module2018
- SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation2018
- KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressors2017
- Face Alignment Across Large Poses: A 3D Solution2016
- Deep Head Pose: Gaze-Direction Estimation in Multimodal VideoIEEE Transactions on Multimedia, 2015
- Real Time Head Pose Estimation from Consumer Depth Cameras2011