Single Camera Face Position-Invariant Driver's Gaze Zone Classifier Based on Frame-Sequence Recognition Using 3D Convolutional Neural Networks.
Catherine LollettMitsuhiro KamezakiShigeki SuganoPublished in: Sensors (2022)
Keyphrases
- object tracking
- single camera
- multiple cameras
- head motion
- convolutional neural networks
- multi camera
- partial occlusion
- gaze estimation
- convolutional network
- image sequences
- appearance model
- multi camera tracking
- eye tracking
- field of view
- human faces
- facial expressions
- frame rate
- head movements
- face images
- affine invariant
- camera calibration
- eye movements
- data fusion