A Driver Fatigue Detection Method Based on Facial Motion Unit Recognition
A driver fatigue and motion unit technology, applied in diagnostic recording/measurement, medical science, sensors, etc., can solve the problems of subjectivity, non-real-time, and expensive equipment in the subjective questionnaire method, and achieve convenient and practical visual information, improve efficiency effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0030] The driver's fatigue detection method based on facial motion unit recognition of the present invention comprises the following steps:
[0031] 1) Locate the face area from the video sequence;
[0032] 2) Locate and divide the key feature points of the face;
[0033] 3) Extract motion features from the corresponding areas of the face in multiple frames of images;
[0034] 4) Classify and identify the extracted motion features and mark them with the motion unit AU;
[0035] 5) Detect fatigue through facial motion units.
[0036] The specific method of locating the face area from the video sequence in the above step 1) is: using the face detection algorithm based on AdaBoost (adaptive enhanced learning algorithm) proposed by Viola (Viola), the method first calculates the different areas of the picture Haar-like (Haar-like) eigenvalues, and then use the adaptive reinforcement learning algorithm (AdaBoost) to train the cascaded classifier; finally, the eigenvalues are p...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 