Fatigue detection method and apparatus, electronic device, and readable storage medium
By performing state detection and differential calculation on the driver's facial temporal images, the fatigue time window is determined, which solves the problem of insufficient accuracy in fatigue driving detection in the existing technology and achieves higher detection accuracy and reliability.
CN116434320BActive Publication Date: 2026-07-17丰图科技(深圳)有限公司
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 丰图科技(深圳)有限公司
- Filing Date
- 2021-12-30
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies for fatigue driving detection are not accurate enough and are prone to false alarms due to misrecognition of facial movements.
Method used
By acquiring temporal images of the face of the object to be inspected, state detection is performed to determine the target fatigue time window and its adjacent target state time windows, and differential calculation is performed to detect fatigue state and reduce the influence of noise.
Benefits of technology
It improves the accuracy of fatigue detection, reduces the possibility of false alarms, and enhances the reliability of detection.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116434320B_ABST
Abstract
Embodiments of the present application provide a fatigue detection method and device, electronic equipment and readable storage medium, and relate to the technical field of image processing. The embodiments of the present application obtain a face time sequence image of a to-be-detected object, perform state detection on the face time sequence image, obtain state time sequence information of the to-be-detected object, determine a target fatigue time window of the to-be-detected object and a target state time window adjacent to the target fatigue time window according to the state time sequence information, and then perform difference calculation on state information corresponding to the target fatigue time window and state information corresponding to the target state time window, so as to detect whether the to-be-detected object is in a fatigue state, reduce the influence of detection noise, and effectively improve the accuracy of fatigue detection.
Need to check novelty before this filing date? Find Prior Art