End-cloud cooperative fatigue driving detection method based on dynamic candidate time sequence
The invention is suitable for the technical field of computer vision detection, and provides an end-cloud cooperative fatigue driving detection method based on a dynamic candidate time sequence, and the method comprises the following steps: obtaining portrait image frame data; analyzing the portrait...
Saved in:
Main Authors | , , , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
24.11.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention is suitable for the technical field of computer vision detection, and provides an end-cloud cooperative fatigue driving detection method based on a dynamic candidate time sequence, and the method comprises the following steps: obtaining portrait image frame data; analyzing the portrait image frame data according to the position estimation model to obtain a to-be-detected image; storing the to-be-detected image according to the dynamic candidate sequence; processing the to-be-detected image according to the fatigue distraction detection model to obtain a detection result; and uploading a detection result to the cloud. According to the method based on end-cloud collaboration, the fatigue driving behavior can be detected in real time on low-computing-power end-side equipment, the occupation of computing resources is reduced by using a multi-task model, the false detection rate of an end-side recognition result is reduced by adopting an end-cloud collaboration computing framework, and finally, the f |
---|---|
Bibliography: | Application Number: CN202311164658 |